M1 Max (24-core GPU, 32 GB)
2 records across 2 models (quants: Q4_K - Medium).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Max (24-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 93.859194 | 1582.032366 | – | 0.7243009050000001 | – | – | sourced | – | source |
| M1 Max (24-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 17.355148333333332 | 155.93443555555555 | – | 7.862980407555557 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085