Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Community benchmark: RTX Pro 4000 Blackwell, qwen3.8-flash-next IQ3_S (bench --long)

Open Beginner friendly
  • Is something wrong?
#2,182 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
1/5
Estimated time
Under an hour
Newbie friendliness
72/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Active
Tech stack
cpp, linux
Domain
performance

Research direction

Start with the benchmark procedure and results in this issue, then compare the reported command and measurements with the existing community benchmark entries or documentation. Add this RTX PRO 4000 Blackwell run, preserving its speed-only caveat and configuration details; done when the benchmark is recorded consistently with the other entries.

Written by the indexing model from the issue text.

Description

Community benchmark on NVIDIA RTX PRO 4000 Blackwell

Measured on 2026-10-12 with tools/strata_bench.py (suite 1, 3 runs per test, medians with ranges). Speeds are the engine's own timings; first-token times are measured by the client over HTTP. Speed only: no correctness check was run.

Hardware and software

  • GPU and VRAM: NVIDIA RTX PRO 4000 Blackwell, 24 GiB VRAM
  • CPU: Intel(R) Xeon(R) Gold 6138 CPU @ 2.00GHz (60 cores, 60 threads); installed RAM: 220.5 GiB; storage: not measured
  • OS: Linux 6.12.0-211.49.1.el10_2.x86_64; GPU driver: 580.105.08; CUDA: 13.0
  • Strata: project 0.1.43.1, commit a0116b27; engine 0.1.43.1
  • Background workloads and power limits: not recorded

Model and configuration

  • Model and quantization: qwen3.8-flash-next-iq3_s
  • Context: 131072 tokens; parallel slots: 1
  • Settings: the install's own configuration, unchanged; thinking off for the suite; temperature 0
strata --pack iq3_s --native Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile expert-profile.bin --expert-cache auto --prefill auto --spec 4 --mtp rt --max-context 131072 --kv int8 --ple-io ram --kv-resident 32768 --vision --vram-reserve-mib 700 --pcie-frac 0.35 --spec-min-p 0.70 --adapt-every 1 --adapt-swaps 160 --adapt-decay 0.97

Method

Run by python tools/strata_bench.py --long against the HTTP API of a Strata server (started by the benchmark from the install configuration); model loading is not timed. One warm-up chat and a 1K prompt are discarded first. Every prompt starts with a unique tag, so the conversation cache cannot help the fresh-prompt tests.

  • short chat: the three questions of tools/ab_engine.py, up to 100 new tokens, 3 runs
  • 4K / 16K prompts: generated word lists sized by a calibration request, 24 new tokens, 3 fresh prompts each
  • agent session: system prompt and four tools, then 5 turns that each add about 1500 words of a project file and continue from the model's own earlier answers (the way agent clients resend a conversation), 64 new tokens per turn, 3 sessions; the cache numbers come from the answer's usage (cached_tokens) and timings (prompt_n)
  • concurrency (when run): N requests sent at the same moment, total tokens over the wall time of the burst, latency over all requests

Results

Configuration Actual prompt tokens Reused tokens Generated tokens Runs Prompt tok/s median and range Decode tok/s median and range TTFT seconds median and range
short chat 46 (43-51) 0 100 (100-100) 9 not measured 58.2 (46.8-64.8) 0.53 (0.46-0.64)
4K prompt, fresh 4019 (4019-4019) 0 (0-0) 24 cap 3 1232.9 (1197.8-1247.0) not measured 3.30 (3.26-3.40)
16K prompt, fresh 16058 (16058-16058) 0 (0-0) 24 cap 3 2086.8 (1904.3-2102.7) not measured 7.77 (7.71-8.50)
32K prompt, fresh 32049 (32049-32049) 0 (0-0) 24 cap 3 1956.1 (1814.4-1960.3) not measured 16.52 (16.48-17.79)
agent session, follow-up turns 14448 (14429-14467) at the last turn see below up to 64 3 see below 75.7 (49.9-92.0) 3.40 (3.09-3.51)

Ranges are the lowest and highest of the runs; Runs counts requests that returned a token.

Agent session (conversation cache)

Cache hit over the follow-up turns: 68.8 % (68.8-68.8); earlier-turn tokens read again per session: 3 (3-3) (earlier turns that the cache did not hold; the 13634 (13633-13634) new tokens of the files are read once); first turn (nothing cached) first token: 1.99 s (1.94-2.23).

Turn (run 1) Prompt tokens Reused Read Prompt tok/s First token (s) Decode tok/s
0 609 0 609 277.8 2.229 35.7
1 3712 631 3081 896.1 3.486 53.2
2 5245 3775 1470 472.4 3.156 49.9
3 8689 5309 3380 982.6 3.495 70.9
4 11577 8717 2860 845.9 3.46 87.7
5 14448 11602 2846 856.5 3.402 71.3

Per-request data: results.json. Engine log lines from the start: engine-log-excerpt.txt (when this run started the server).

Correctness and limitations

Not measured: this is a speed suite. The conversation uses the model's own replies, so token counts differ a little between runs. Machine details come from the server, nvidia-smi/rocm-smi and the OS; background load and power limits are not recorded. Total time of the suite: 183 s.

Dominant language
C++
Stars
11.6k
Forks
1k
No merged PRs in 30d

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from Niko1221/Strata

All issues in Niko1221/Strata

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.