M1 Pro (14-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M1 Pro (14-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 19.971878777777775 | 173.08191844444443 | – | 7.230578513999999 | – | – | sourced | – | source |
| M1 Pro (14-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 71.01946466666666 | 1063.8479185555557 | – | 1.1336526296666667 | – | – | sourced | – | source |
| M1 Pro (14-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 10.399665111111112 | 88.86977233333333 | – | 14.166348648222224 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085