Llama 3.1 8B Instruct › Apple M4 Max (40-core GPU)
Llama 3.1 8B Instruct on the Apple M4 Max (40-core GPU)
Best measured: 52.9 tokens/s generation and 632 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 86.7 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 54.5 | 656 | LocalScore avg | LocalScore rank 97/422 | LocalScore (localscore.ai) |
| Q4_K_M | llamafile | 52.9 | 632 | LocalScore avg | LocalScore rank 98/422 | LocalScore (localscore.ai) |
| Q4_K_M | llamafile | 47.9 | 566 | LocalScore avg | LocalScore rank 100/422 | 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.
No card yet?
Try it on a rented GPU (RunPod)Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.
All results for the Apple M4 Max (40-core GPU) · Llama 3.1 8B Instruct on other hardware