M1 Max (24-core GPU, 64 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Max (24-core GPU, 64 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 32.11692033333334 | 306.18835666666666 | – | 3.9939120186666677 | – | – | sourced | – | source |
| M1 Max (24-core GPU, 64 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 105.66463296296295 | 1669.4850333333334 | – | 0.6893040093333332 | – | – | sourced | – | source |
| M1 Max (24-core GPU, 64 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 15.135508527777777 | 140.19277200000002 | – | 8.830140840277778 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085