M2 Max (38-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Max (38-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 44.66334788888888 | 473.660562 | – | 2.4878861063333333 | – | – | sourced | – | source |
| M2 Max (38-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 152.97702255555558 | 2551.365566666667 | – | 0.44196865744444436 | – | – | sourced | – | source |
| M2 Max (38-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 20.586609111111116 | 225.5740881111111 | – | 4.983570564777778 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085