M4 Pro (16-core GPU, 24 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Pro (16-core GPU, 24 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 30.508745533333336 | 298.0409531777778 | – | 4.201011161111111 | – | – | sourced | – | source |
| M4 Pro (16-core GPU, 24 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 110.94556159259258 | 1823.817922962963 | – | 0.6715746882962962 | – | – | sourced | – | source |
| M4 Pro (16-core GPU, 24 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 15.160405666666666 | 144.2954926666667 | – | 8.903966308944444 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085