M2 Pro (16-core GPU, 16 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 Pro (16-core GPU, 16 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 24.331960740740744 | 224.56031674074077 | – | 5.574148605037037 | – | – | sourced | – | source |
| M2 Pro (16-core GPU, 16 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 91.14859188888887 | 1328.2018266666669 | – | 0.9017461759444444 | – | – | sourced | – | source |
| M2 Pro (16-core GPU, 16 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 13.350706388888891 | 118.980526 | – | 10.621650037111111 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085