THE SPEED TOOL: THE BUILD'S REPORT (v2) Built from the research hub's hardware roster, rows.json sha256 128a3b2630f5f60c906a5730b6276392538359e923239fda4753b9a6d8639130 (1,054 rows). Every figure a pick shows is one measured run: among the runs of a card, model and engine that measured the most of the three inputs, the lower-middle one by writing speed. Nothing is averaged. == WHAT COUNTS, AND WHAT THE RULES LEFT OUT writing speed 47 pooled; left out: R2 18, R3 8, R5 23, R6 10, R7 8, R8 29 wait 14 pooled; left out: R2 18, R3 5, R4 12, R5 31, R8 9 reading speed 7 pooled; left out: R3 3, R5 16, R7 1 Rules: R2 not a graphics card; R3 no model named; R4 more than one request at a time; R5 a long prompt or a filled window; R6 a reviewed exclusion; R7 another version of the same engine; R8 not at the card's stock power limit == EVERY OPTION (22) card | model | engine version | writing, tok/s (N; range) | wait, s (N; range) | reading, tok/s (N; range) NVIDIA GeForce RTX 3080 (10 GB) | gemma4:26b | not stated | 34.4 (1) | - | - NVIDIA GeForce RTX 3080 (10 GB) | mistral-small3.2:24b | not stated | 5.1 (1) | - | - Two NVIDIA GeForce RTX 3080 (10 GB each) | gemma4:26b | 0.32.13 | 115.4 (6; 113.8-124.7) | - | - Two NVIDIA GeForce RTX 3080 (10 GB each) | mistral-small3.2:24b | 0.32.13 | 44.6 (2; 44.6-44.7) | - | - NVIDIA GeForce RTX 3090 (24 GB) | Gemma 4 12B · Ollama | 0.34.4 | 85.0 (1) | 0.44 (1) | - NVIDIA GeForce RTX 3090 (24 GB) | Gemma 4 12B · vLLM | 0.30.0 | 82.7 (1) | 0.21 (1) | - NVIDIA GeForce RTX 3090 (24 GB) | gemma4:26b | 0.32.13 | 136.3 (4; 135.2-146.3) | - | - NVIDIA GeForce RTX 3090 (24 GB) | mistral-nemo:12b-instruct-2407 | 0.32.13 | 74.9 (10; 60.4-88.2) | 0.51 (5; 0.48-0.55) | - NVIDIA GeForce RTX 3090 (24 GB) | mistral-small3.2:24b | 0.32.13 | 46.9 (1) | - | - NVIDIA GeForce RTX 3090 Ti (24 GB) | gemma4:26b | 0.32.13 | 147.4 (2; 147.4-147.6) | - | - NVIDIA GeForce RTX 3090 Ti (24 GB) | mistral-small3.2:24b | 0.32.13 | 57.4 (1) | - | - NVIDIA GeForce RTX 3090 Ti (24 GB) | Qwen3.8-Flash-Next · llama.cpp | b11514 | 22.7 (1) | 2.04 worked out at 519 tokens | 255 (1) NVIDIA GeForce RTX 3090 Ti (24 GB) | Qwen3.8-Flash-Next · the Strata engine | 0.1.39 | 98.3 (1) | 0.24 worked out at 519 tokens | 2,143 (1) NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) | gemma4:26b | 0.32.13 | 118.4 (4; 116.1-121.4) | 0.35 (4; 0.33-0.44) | - NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) | minicpm-v4.5 | 0.32.13 | 86.8 (1) | 0.15 (1) | - NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) | mistral-small3.2:24b | 0.32.13 | 28.8 (2; 28.8-28.9) | 0.21 (2; 0.21-0.21) | - NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) | Qwen3.8-Flash-Next · llama.cpp | 3cf03257 | 22.5 (3; 22.5-32.5) | 0.97 worked out at 519 tokens | 534 (2; 212-534) NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) | Qwen3.8-Flash-Next · the Strata engine | 0.1.25 | 85.6 (1) | 0.24 worked out at 519 tokens | 2,148 (1) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) | gemma4:26b | not stated | 205.9 (1) | - | - NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) | mistral-small3.2:24b | not stated | 92.8 (1) | - | - NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) | Qwen3.8-Flash-Next · llama.cpp | 3cf03257 | 102.9 (1) | 0.32 worked out at 519 tokens | 1,619 (1) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) | Qwen3.8-Flash-Next · the Strata engine | 0.1.39 | 205.3 (1) | 0.13 worked out at 519 tokens | 3,920 (1) == VERSIONS SHOWN (R7) NVIDIA GeForce RTX 3090 (24 GB) · Gemma 4 12B · Ollama: 0.34.4 (the newer of the two versions measured (0.32.13 on 2026-09-28, 0.34.4 on 2026-10-01)) NVIDIA GeForce RTX 3090 (24 GB) · Gemma 4 12B · vLLM: 0.30.0 (the newer of the two versions measured (0.27.1 on 2026-09-28, 0.30.0 on 2026-10-01)) NVIDIA GeForce RTX 3090 (24 GB) · gemma4:26b · Ollama: 0.32.13 (the version is stated; the other rows' exhibit does not state one) NVIDIA GeForce RTX 3090 (24 GB) · mistral-small3.2:24b · Ollama: 0.32.13 (the version is stated; the other rows' exhibit does not state one) NVIDIA GeForce RTX 3090 Ti (24 GB) · Qwen3.8-Flash-Next · llama.cpp: b11514 (the current build, 452 commits after 3cf03257, per its exhibit) == POWER LIMITS (R8) NVIDIA GeForce RTX 3080 (10 GB) · gemma4:26b: every limit counts (not stated) NVIDIA GeForce RTX 3080 (10 GB) · mistral-small3.2:24b: every limit counts (not stated) Two NVIDIA GeForce RTX 3080 (10 GB each) · gemma4:26b: every limit counts (250 W each, 500 W for both cards; 300 W each, 600 W for both cards; not stated) Two NVIDIA GeForce RTX 3080 (10 GB each) · mistral-small3.2:24b: every limit counts (250 W each, 500 W for both cards; 300 W each, 600 W for both cards) NVIDIA GeForce RTX 3090 (24 GB) · Gemma 4 12B · Ollama: every limit counts (300 W) NVIDIA GeForce RTX 3090 (24 GB) · Gemma 4 12B · vLLM: every limit counts (300 W) NVIDIA GeForce RTX 3090 (24 GB) · gemma4:26b: the card's stock limit, 350 W; 6 rows at other limits left out NVIDIA GeForce RTX 3090 (24 GB) · mistral-nemo:12b-instruct-2407: every limit counts (300 W) NVIDIA GeForce RTX 3090 (24 GB) · mistral-small3.2:24b: the card's stock limit, 350 W; 3 rows at other limits left out NVIDIA GeForce RTX 3090 Ti (24 GB) · gemma4:26b: the card's stock limit, 450 W; 8 rows at other limits left out NVIDIA GeForce RTX 3090 Ti (24 GB) · mistral-small3.2:24b: the card's stock limit, 450 W; 3 rows at other limits left out NVIDIA GeForce RTX 3090 Ti (24 GB) · Qwen3.8-Flash-Next · llama.cpp: every limit counts (300 W) NVIDIA GeForce RTX 3090 Ti (24 GB) · Qwen3.8-Flash-Next · the Strata engine: every limit counts (300 W) NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) · gemma4:26b: the card's stock limit, 95 W; 10 rows at other limits left out NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) · minicpm-v4.5: the card's stock limit, 95 W; 2 rows at other limits left out NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) · mistral-small3.2:24b: the card's stock limit, 95 W; 6 rows at other limits left out NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) · Qwen3.8-Flash-Next · llama.cpp: every limit counts (135–150 W) NVIDIA GeForce RTX 5090 Laptop GPU (24 GB) · Qwen3.8-Flash-Next · the Strata engine: every limit counts (135–150 W) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) · gemma4:26b: every limit counts (420 W) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) · mistral-small3.2:24b: every limit counts (420 W) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) · Qwen3.8-Flash-Next · llama.cpp: every limit counts (300 W) NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB) · Qwen3.8-Flash-Next · the Strata engine: every limit counts (300 W) == THE STARTING NUMBERS writing speed 136.3: 136.274 tokens a second: Ollama 0.32.13, Q4_K_M, 350 W (the card's stock limit), a 4,096-token window, 256 tokens out (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench). It is the card list's NVIDIA GeForce RTX 3090 (24 GB) · gemma4:26b: our most-measured card and its most-measured model, the lower-middle of 4 runs at the stock limit (135.2–146.3). wait 0.51: 510.56 ms: mistral-nemo:12b-instruct-2407, Q3_K_M with an 8-bit cache, Ollama 0.32.13, 300 W, a 4,096-token window, a 519-token question, one request (The quantization ladder). It is the card list's NVIDIA GeForce RTX 3090 (24 GB) · mistral-nemo:12b-instruct-2407, measured in the same run as that pair's 74.9; five waits were measured, 0.48–0.55 s. reading speed 2271: Our NVIDIA GeForce RTX 3090 (24 GB) reading a 98,000-token document. Its article doesn't name the model, so the card list can't offer this figure. Settings: a 519-token question; an answer of 3 paragraphs; prose; 238 words a minute. == EVERY ROW THE RULES LEFT OUT (191) R2 not a graphics card: a processor-only machine | writing speed | 11.0 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 11.1 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 12.7 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 13.3 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 13.6 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 14.6 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 15.4 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 2.7 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 24.7 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 3.3 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 31.5 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 4.4 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 5.0 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 5.2 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 6.0 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 7.1 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 7.5 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | writing speed | 9.1 tok/s | decode, median of five scored runs (Two Hours at 12 tok/s — On Battery § the-one-table-to-remember) R2 not a graphics card: a processor-only machine | wait | 11.4 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 14.1 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 14.1 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 16.0 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 22.2 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 24.6 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 25.6 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 26.4 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 3.7 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 35.4 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 4.0 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 4.9 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 6.9 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 8.1 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 8.5 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 82.4 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 9.9 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R2 not a graphics card: a processor-only machine | wait | 97.7 s | time to first token, median of five cold-prefix runs (Two Hours at 12 tok/s — On Battery § the-wait-prefill-is-the-real-cpu-tax) R3 no model named: its article names no model a reader can pick | writing speed | 137 | decode, tokens a second (The cost to purchase and run a very capable home AI rig § what-kind-of-performance-to-expect) R3 no model named: its article names no model a reader can pick | writing speed | 53 | decode, tokens a second (The cost to purchase and run a very capable home AI rig § what-kind-of-performance-to-expect) R3 no model named: its article names no model a reader can pick | writing speed | 73.327 | decode once the window is full, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R3 no model named: its article names no model a reader can pick | writing speed | 79.740 | decode once the window is full, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R3 no model named: its article names no model a reader can pick | writing speed | 80.056 | decode once the window is full, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R3 no model named: its article names no model a reader can pick | writing speed | 207.7 tok/s | writing speed (The Typist and the Developer § one-card-both-jobs-at-once) R3 no model named: its article names no model a reader can pick | writing speed | 61.5 tok/s | decode once the window is full, tokens a second (Two 3080s against one 3090, and the cap decides § what-about-a-long-document) R3 no model named: its article names no model a reader can pick | writing speed | 72.8 | decode once the window is full, tokens a second (Two 3080s against one 3090, and the cap decides § what-about-a-long-document) R3 no model named: its article names no model a reader can pick | wait | 0.08 s | time to the first token (The cost to purchase and run a very capable home AI rig § what-kind-of-performance-to-expect) R3 no model named: its article names no model a reader can pick | wait | 0.30 s | time to the first token (The cost to purchase and run a very capable home AI rig § what-kind-of-performance-to-expect) R3 no model named: its article names no model a reader can pick | wait | 1.01 s | time to the first token (The cost to purchase and run a very capable home AI rig § what-kind-of-performance-to-expect) R3 no model named: its article names no model a reader can pick | wait | 30.04 s | time to the first token, seconds (Two 3080s against one 3090, and the cap decides § what-about-a-long-document) R3 no model named: its article names no model a reader can pick | wait | 46.64 s | time to the first token, seconds (Two 3080s against one 3090, and the cap decides § what-about-a-long-document) R3 no model named: its article names no model a reader can pick | reading speed | 2,270.547 | prompt reading, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R3 no model named: its article names no model a reader can pick | reading speed | 2,549.966 tokens a second | prompt reading, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R3 no model named: its article names no model a reader can pick | reading speed | 2,628.756 | prompt reading, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R4 more than one request at a time | wait | 525.93 | first token, ms (A laptop, asked the desktop's questions § the-tables) R4 more than one request at a time | wait | 528.06 | first token, ms (A laptop, asked the desktop's questions § the-tables) R4 more than one request at a time | wait | 694.10 | first token, ms (A laptop, asked the desktop's questions § the-tables) R4 more than one request at a time | wait | 702.42 | first token, ms (A laptop, asked the desktop's questions § the-tables) R4 more than one request at a time | wait | 1,068.577 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 1,641.068 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 2,244.823 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 20,935.24 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 3,333.177 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 417.849 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 5,365.722 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R4 more than one request at a time | wait | 822.939 | the wait for the first token, 95th percentile, ms (Ollama and vLLM on one RTX 3090 § requests-at-once) R5 a long prompt or a filled window | writing speed | 56.174 (56.039–56.374) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R5 a long prompt or a filled window | writing speed | 72.159 (72.024–72.171) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R5 a long prompt or a filled window | writing speed | 102.5 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | writing speed | 115.2 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | writing speed | 13.0 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 13.993 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 14.2 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 17.5 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | writing speed | 17.681 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 172.325 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | writing speed | 189.155 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | writing speed | 19.4 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 19.620 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 20.7 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 21.257 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 26.6 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | writing speed | 38.576 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | writing speed | 69.8 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 76.337 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | writing speed | 81.452 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 87.1 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § writing-the-answer-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | writing speed | 92.571 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | writing speed | 124.975 | decode at a deeper context tier (The free speed wasn't free — the runtime dividend, traced to one commit § the-day-the-box-got-faster) R5 a long prompt or a filled window | wait | 721.95 | first token, ms (A laptop, asked the desktop's questions § the-tables) R5 a long prompt or a filled window | wait | 744.92 | first token, ms (A laptop, asked the desktop's questions § the-tables) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 1.06 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 1.9 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 1.92 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 11.5 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | wait | 12.1 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 12.14 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 125.6 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 130.90 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 138.02 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 15.84 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 16.87 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 19.1 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 2.52 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | wait | 20.91 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | wait | 204.4 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 26.63 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | wait | 321.8 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | wait | 45.2 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | wait | 47.6 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 50.0 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 51.05 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 528.72 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 545.1 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 566.57 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | wait | 6.37 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 7.6 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | wait | 73.3 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window: a wait measured at a 4,038-token prompt, over 600 | wait | 9.5 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-q2-0-pair-the-laptop) R5 a long prompt or a filled window | wait | 94.22 | first word, seconds (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | reading speed | 1,362.8 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | reading speed | 1,539.1 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | reading speed | 2,535.0 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 2,655.1 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | reading speed | 2,671.6 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 2,705.0 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | reading speed | 226.1 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 232.3 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 234.9 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | reading speed | 242.3 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 244.9 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R5 a long prompt or a filled window | reading speed | 255.1 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | reading speed | 4,908.1 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | reading speed | 5,143.9 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-desktop-card-one-engine-a-night) R5 a long prompt or a filled window | reading speed | 626.7 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R5 a long prompt or a filled window | reading speed | 640.9 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-first-word-the-laptop-the-iq3-s-file) R6 a reviewed exclusion: by its label, one model split over two different cards | writing speed | 71.48 | decode, tokens a second, split, seats stopped (A Short History of Mistral § what-a-power-cap-actually-costs) R6 a reviewed exclusion: by its label, one model split over two different cards, with other work on them | writing speed | 38.22 | decode, tokens a second, split, seats up (A Short History of Mistral § what-a-power-cap-actually-costs) R6 a reviewed exclusion: by its label, a second clock on a run its (scored) row already counts | writing speed | 78.118 | decode, tokens a second (the server's own clock) (Ollama and vLLM on one RTX 3090 § one-request-at-a-time) R6 a reviewed exclusion: by its label, a second clock on a run its (scored) row already counts | writing speed | 85.553 | decode, tokens a second (the server's own clock) (Ollama and vLLM on one RTX 3090 § one-request-at-a-time) R6 a reviewed exclusion: by row, Ollama 0.32.9, before the upstream fix its own exhibit traces (the after-upgrade reading is 202-214 on 0.32.13) | writing speed | 139.55 (n=6, range 137.75–150.49) | sealed bench median decode (The free speed wasn't free — the runtime dividend, traced to one commit § the-day-the-box-got-faster) R6 a reviewed exclusion: by row, a rounded reprint of 126.650 in “RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench”; the more precise copy counts | writing speed | 126.7 | decode summed across conversations, tokens a second (Two 3080s against one 3090, and the cap decides § the-full-concurrency-ladder) R6 a reviewed exclusion: by row, a rounded reprint of 134.754 in “RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench”; the more precise copy counts | writing speed | 134.8 | decode summed across conversations, tokens a second (Two 3080s against one 3090, and the cap decides § the-full-concurrency-ladder) R6 a reviewed exclusion: by row, a rounded reprint of 136.139 in “RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench”; the more precise copy counts | writing speed | 136.1 | decode, tokens a second (Two 3080s against one 3090, and the cap decides § how-fast-does-each-one-write) R6 a reviewed exclusion: by row, a rounded reprint of 33.265 in “RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench”; the more precise copy counts | writing speed | 33.3 | decode, tokens a second (Two 3080s against one 3090, and the cap decides § how-fast-does-each-one-write) R6 a reviewed exclusion: by row, a rounded reprint of 47.838 in “RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench”; the more precise copy counts | writing speed | 47.8 | decode, tokens a second (Two 3080s against one 3090, and the cap decides § how-fast-does-each-one-write) R7 another version of the same engine on this card (not stated; 0.32.13 is shown: the version is stated; the other rows' exhibit does not state one) | writing speed | 126.12 tokens a second | decode, tokens a second (A Short History of Mistral § what-we-measured-on-two-cards-in-one-box) R7 another version of the same engine on this card (not stated; 0.32.13 is shown: the version is stated; the other rows' exhibit does not state one) | writing speed | 136.49 | decode, tokens a second (A Short History of Mistral § what-a-power-cap-actually-costs) R7 another version of the same engine on this card (not stated; 0.32.13 is shown: the version is stated; the other rows' exhibit does not state one) | writing speed | 34.13 tokens a second | decode, tokens a second (A Short History of Mistral § what-we-measured-on-two-cards-in-one-box) R7 another version of the same engine on this card (not stated; 0.32.13 is shown: the version is stated; the other rows' exhibit does not state one) | writing speed | 48.18 | decode, tokens a second (A Short History of Mistral § what-a-power-cap-actually-costs) R7 another version of the same engine on this card (not stated; 0.32.13 is shown: the version is stated; the other rows' exhibit does not state one) | writing speed | 50.02 | decode, tokens a second (A Short History of Mistral § what-a-power-cap-actually-costs) R7 another version of the same engine on this card (3cf03257; b11514 is shown: the current build, 452 commits after 3cf03257, per its exhibit) | writing speed | 22.490 | writing speed, tokens a second (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R7 another version of the same engine on this card (0.27.1; 0.30.0 is shown: the newer of the two versions measured (0.27.1 on 2026-09-28, 0.30.0 on 2026-10-01)) | writing speed | 78.126 | decode, tokens a second (scored) (Ollama and vLLM on one RTX 3090 § one-request-at-a-time) R7 another version of the same engine on this card (0.32.13; 0.34.4 is shown: the newer of the two versions measured (0.32.13 on 2026-09-28, 0.34.4 on 2026-10-01)) | writing speed | 85.216 | decode, tokens a second (scored) (Ollama and vLLM on one RTX 3090 § one-request-at-a-time) R7 another version of the same engine on this card (3cf03257; b11514 is shown: the current build, 452 commits after 3cf03257, per its exhibit) | reading speed | 239.7 | prompt rate, tokens a second, the engine's clock (Why the first word comes sooner: the Strata engine and llama.cpp on Qwen3.8-Flash-Next, the full bench § the-24-gb-desktop-card-both-engines-in-one-window) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 155.231 | summed tokens/s (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 155.251 | tokens/s (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 155.288 | tokens/s (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 44.702 | tokens/s (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 44.897 | tokens/s (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 121.733 (121.722–121.762) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 155.712 (155.641–155.908) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 165.656 (165.545–166.175) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | writing speed | 44.946 (44.917–44.963) | tokens/s (spread of three) (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 146.780, 19,428 MiB | decode at the full window, and the memory it used (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-fits-and-what-the-cache-costs) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 159.410 tok/s, 21,008 MiB | decode at the full window, and the memory it used (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-fits-and-what-the-cache-costs) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 126.650 | decode summed across conversations, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 134.754 | decode summed across conversations, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 145.817 | decode summed across conversations, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 146.996 | decode summed across conversations, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 147.201 | decode summed across conversations, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § three-more-arms) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 136.139 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 145.908 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 147.599 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § the-two-models-want-different-caps) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 147.823 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 33.265 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 42.969 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 47.838 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 53.354 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 450 W, the stock limit, was measured too | writing speed | 56.936 | decode, tokens a second (RTX 3090 vs RTX 3090 Ti: an inference and diffusion bench § what-a-power-cap-takes-and-what-each-card-does-at-its-own) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 124.7 tok/s, 19,415 MiB | decode at the full window, and the memory it used (Two 3080s against one 3090, and the cap decides § what-the-cache-type-costs) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 133.6 tok/s, 20,995 MiB | decode at the full window, and the memory it used (Two 3080s against one 3090, and the cap decides § what-the-cache-type-costs) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 125.6 | decode, tokens a second (Two 3080s against one 3090, and the cap decides § how-fast-does-each-one-write) R8 not at the card's stock power limit: 350 W, the stock limit, was measured too | writing speed | 33.1 | decode, tokens a second (Two 3080s against one 3090, and the cap decides § how-fast-does-each-one-write) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 132.94 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 191.65 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 203.72 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 208.97 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 336.23 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 371.01 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 372.92 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 401.70 | first token, ms (A laptop, asked the desktop's questions § the-tables) R8 not at the card's stock power limit: 95 W, the stock limit, was measured too | wait | 439.78 | first token, ms (A laptop, asked the desktop's questions § the-tables)