M2 Pro (19-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 Pro (19-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 26.311742333333328 | 261.761128 | – | 4.701914784666666 | – | – | sourced | – | source |
| M2 Pro (19-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 100.2557703111111 | 1487.5642871333334 | – | 0.8063303454888889 | – | – | sourced | – | source |
| M2 Pro (19-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 14.116209888888887 | 137.32948566666667 | – | 9.101328361111113 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085