M1 Pro (14-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Pro (14-core GPU, 16 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 20.14017855555555 | 176.96636692592594 | – | 6.991519057185186 | – | – | sourced | – | source |
| M1 Pro (14-core GPU, 16 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 71.81051661111111 | 1040.067598027778 | – | 1.1483909050555556 | – | – | sourced | – | source |
| M1 Pro (14-core GPU, 16 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 10.8301478 | 92.4920569777778 | – | 13.4879233686 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085