# standard benchmark: NVIDIA GeForce RTX 3090 Protocol `strata-qwen38-thinking-v1-draft.1` (draft), run `20261026T234702Z-0f07e24d`, started 2026-10-26T23:47:02Z. **Status: complete.** Written by ` bench run`. The machine-readable result is [results.json](results.json); every request, its raw usage and timings and the client event offsets are in [outputs.jsonl](outputs.jsonl). ## Hardware and software - GPU: NVIDIA GeForce RTX 3090 (24.0 GiB dedicated) - CPU: Intel(R) Core(TM) i9-14900KS; RAM: 110.0 GiB - Storage of the model files: not measured - OS: NixOS 26.05 (Yarara) 6.18.55; drivers: gpu-driver 595.71.05; runtime: cuda 13.2 - commit: `4b9e05a2a806a3fe24f7b2560d98626c37dade35`; engine 0.1.51; source build - Background work: not measured ## Model and configuration - Model: qwen3.8-flash-next-iq3_s; quantization IQ3_S; revision not measured; source revision not measured - Files: `Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf` `4c1eb2ceb4915e11...`; `Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf` `316b46f3a2dbd68c...` - Track: **default** (lovey 2x3090, 250 W cap, gpu-unlock, setup defaults + --max-context 131072) - Context 131072 tokens; server capacity 1 slot(s) - Sampling: temperature 1.0, top_p 0.95, top_k 20, min_p 0.0, presence_penalty 0.0, repetition_penalty 1.0, reasoning_effort xhigh; thinking on, preserved - Engine options: `config.json`; chat template: `provenance/chat_template.jinja` ## Method The frozen requests of `bench/prompts/standard-v1` (corpus `e75eff8b9feea04f...`) were sent over loopback HTTP, streaming, one at a time, in this order: 1 warm-up (excluded), 3 repetitions of the short, 4K and 16K prompts, and the twelve sanity checks. Prompt and decode speed are the engine's own `timings`; time to first token is the client's monotonic clock from dispatch to the first nonempty reasoning, answer or tool-call delta. No request was retried. Time after the model loaded: 1 min 31 s. ## Results | Case | Prompt tok/s | Decode tok/s | TTFT s | First answer s | Total s | Capped | | --- | --- | --- | --- | --- | --- | --- | | short | n/a | 130.7 (124.1-135.6) n=3 | 0.35 (0.34-0.41) n=3 | 1.17 (0.89-2.55) n=3 | 4.2 (3.1-4.2) n=3 | 1/3 | | prompt-4k | 1776.1 (1774.2-1778.0) n=3 | 123.2 (112.6-128.4) n=3 | 2.32 (2.32-2.33) n=3 | 5.30 (4.96-5.64) n=2 | 6.5 (6.3-6.9) n=3 | 3/3 | | prompt-16k | 2937.9 (2934.5-2945.0) n=3 | 124.5 (115.0-131.4) n=3 | 5.61 (5.59-5.61) n=3 | 7.97 (7.79-8.14) n=2 | 9.7 (9.5-10.1) n=3 | 3/3 | Cells are median (min-max) n=samples. Short is a prompt of about 80 tokens: its prompt rate is dominated by the fixed cost of a request, so it is not shown; read prompt speed from prompt-4k and prompt-16k. Capped = requests that reached the 512-token cap, reasoning and answer together. A capped request's total time is the time to the cap, not to an answer, and it has no first-answer time when it was still reasoning. | Phase | Planned | Completed | Truncated | Failed | Skipped | | --- | ---: | ---: | ---: | ---: | ---: | | warmup | 1 | 0 | 1 | 0 | 0 | | performance | 9 | 2 | 7 | 0 | 0 | | sanity | 12 | 12 | 0 | 0 | 0 | | concurrency | 12 | 3 | 9 | 0 | 0 | Sanity checks: **12 of 12**. | Case | Result | Reason | | --- | --- | --- | | I1 | pass | the expected JSON value | | I2 | pass | the expected JSON value | | I3 | pass | the expected JSON value | | I4 | pass | the exact expected text | | R1 | pass | the exact expected text | | R2 | pass | the exact expected text | | R3 | pass | the exact expected text | | R4 | pass | the expected JSON value | | T1 | pass | the expected tool call | | T2 | pass | the expected tool call | | T3 | pass | the expected tool call | | T4 | pass | the expected tool call | Concurrency rounds (four requests released together): | Round | Wall s | Output tokens | Aggregate tok/s | Failed | | ---: | ---: | ---: | ---: | ---: | | 1 | 16.25344 | 1877 | 115.483245 | 0 | | 2 | 15.310917 | 1937 | 126.511038 | 0 | | 3 | 16.230166 | 2048 | 126.184785 | 0 | ## Failures, exclusions and limitations - No request failed. - Excluded from speed summaries: performance-prompt-16k-r3: first_answer_s is not available for this request - Excluded from speed summaries: performance-prompt-4k-r1: first_answer_s is not available for this request - Prompt-prefix reuse is the shared template prefix only; the cache was not emptied between requests, and the expert cache stays warm and evolves. These are not cold-model measurements. - Output caps include reasoning; a request that reaches its cap is `truncated` and fails its sanity check. - The runner cannot see other programs on the machine, the repeat-stop and loop-recovery switches of the server, or the quantization repository's revision; see `missing` in results.json for every value it could not read. - The server had answered 1122 request(s) before this run.