Llama 3.2 1B Instruct › NVIDIA Tesla P40
Llama 3.2 1B Instruct on the NVIDIA Tesla P40
Best measured: 105 tokens/s generation and 2,662 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 189 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 105 | 2,662 | LocalScore avg | LocalScore rank 140/878 | 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 P40 · Llama 3.2 1B Instruct on other hardware