Llama 3.2 1B Instruct › NVIDIA P106-100
Llama 3.2 1B Instruct on the NVIDIA P106-100
Best measured: 70.3 tokens/s generation and 1,758 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 98.1 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 70.3 | 1,758 | LocalScore avg | LocalScore rank 172/878 | 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 P106-100 · Llama 3.2 1B Instruct on other hardware