M1 Pro (16-core GPU, 32 GB)
3 records across 3 models (quants: Q4_K - Medium).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Pro (16-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 21.698664740740742 | 200.28393007407408 | – | 6.2272433256296305 | – | – | sourced | – | source |
| M1 Pro (16-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 77.23935995555556 | 1165.9555193555557 | – | 1.0365038463555556 | – | – | sourced | – | source |
| M1 Pro (16-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 11.619242305555556 | 104.4587133888889 | – | 12.083205306861112 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085