M4 Max (32-core GPU, 36 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Max (32-core GPU, 36 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 48.071329866666666 | 570.2711772 | – | 2.1545828000444445 | – | – | sourced | – | source |
| M4 Max (32-core GPU, 36 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 166.45011455555556 | 3268.880837361111 | – | 0.366560225611111 | – | – | sourced | – | source |
| M4 Max (32-core GPU, 36 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 24.60766388888889 | 273.40494424444444 | – | 4.441582821466667 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085