Llama 3.1 8B Instruct › Apple M3 Max (40-core GPU)
Llama 3.1 8B Instruct on the Apple M3 Max (40-core GPU)
Best measured: 35.6 tokens/s generation and 480 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 68.7 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 45.8 | 583 | LocalScore avg | LocalScore rank 102/422 | LocalScore (localscore.ai) |
| Q4_K_M | llamafile | 25.4 | 377 | LocalScore avg | LocalScore rank 134/422 | 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 M3 Max (40-core GPU) · Llama 3.1 8B Instruct on other hardware