Tesla P40 × Qwen3-Coder-30B-A3B-Instruct-1M
Qwen3-Coder-30B-A3B-Instruct-1M on Tesla P40
29.3best gen tok/s
288best prompt tok/s
640max context tested
1results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 29.3 | 288 | LocalScore ↗ | 512+128 | 4,041 ms | llamafile 0.9.3 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can Tesla P40 run? →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.