qwen2.5-coder on RTX 3090 (24GB) + AMD EPYC 7702P 64-Core Processor (64c) + 252GB
RTX 3090 (24GB) + AMD EPYC 7702P 64-Core Processor (64c) + 252GB
suite suite-v1
cli 0.0.3
signed+NwKPaMRjm…
Embed badgesubmitted Jul 02, 2026Workload results
| Workload | Backend | Model | decode tok/s | prefill tok/s | TTFT | p50 | p95 |
|---|---|---|---|---|---|---|---|
| chat-short | ollama@0.31.1 | qwen2.5-coderQ4_K_M | 69.21tok/s | 402.0tok/s | 326ms | 14.4ms | 14.9ms |
| chat-long | ollama@0.31.1 | qwen2.5-coderQ4_K_M | 65.83tok/s | 2,070.6tok/s | 1,530ms | 15.2ms | 15.6ms |
| concurrent-decode | ollama@0.31.1 | qwen2.5-coderQ4_K_M | 67.64tok/s | — | — | 14.7ms | 15.3ms |
| agent-trace | ollama@0.31.1 | qwen2.5-coderQ4_K_M | 63.63tok/s | 3,518.8tok/s | 483ms | 15.4ms | 17.4ms |
Reproduce on your machine
Same workload, same model, signed at your rig. The exact command that produced this run:
$ pipx install llm-speed && llm-speed bench --model 'qwen2.5-coder' --workload 'chat-short'
Runs in about a minute. Your number lands on the leaderboard signed and linkable. How it's measured.
Embed this run
Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.
[](https://llm-speed.com/r/r_6ahy-dq0f_0)Related benchmarks
- More qwen2.5-coder benchmarks — every backend and rig that has run this model.
- More RTX 3090 (24GB) LLM benchmarks — every model measured on this hardware.
Provenance
- Run ID
- r_6ahy-dq0f_0
- Fingerprint hash
- Public key
- +NwKPaMRjmIfrqAm7KKOOld2RbM1lTa0cHfi0ARmmlo=
- Received
- 2026-07-02 05:12:05