M2 Max (30-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Max (30-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 31.185154777777775 | 325.001513 | – | 3.7657567592222216 | – | – | sourced | – | source |
| M2 Max (30-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 127.58507908333334 | 2031.665092888889 | – | 0.5575502119166668 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085