Qwen2.5 14B Instruct › NVIDIA Tesla P100
Qwen2.5 14B Instruct on the NVIDIA Tesla P100
Best measured: 19.8 tokens/s generation and 193 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 28.3 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 20.5 | 204 | LocalScore avg | LocalScore rank 115/418 | LocalScore (localscore.ai) |
| Q4_K_M | llamafile | 19.1 | 181 | LocalScore avg | LocalScore rank 124/418 | LocalScore (localscore.ai) |
tg128 = generating 128 tokens; pp512 = reading a 512-token prompt (llama-bench). LocalScore averages several prompt and output lengths, so its numbers run lower than tg128.
Rent one by the hour
Rent a GPU on RunPodAffiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.
All results for the NVIDIA Tesla P100 · Qwen2.5 14B Instruct on other hardware