M4 (10-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 (10-core GPU, 32 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 16.809439277777777 | 166.14551366666666 | – | 7.554811377277778 | – | – | sourced | – | source |
| M4 (10-core GPU, 32 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 75.56749613888888 | 1069.8806100277775 | – | 1.2130988726666667 | – | – | sourced | – | source |
| M4 (10-core GPU, 32 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 8.58771625925926 | 79.33710781481481 | – | 15.81842497840741 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085