M4 (10-core GPU, 16 GB)
4 records across 4 models (quants: Q4_0, 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, 16 GB) | Llama 2 7B | Q4_0 | llama.cpp | 24.11 | 221.29 | – | – | 512 | – | sourced | – | source |
| M4 (10-core GPU, 16 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 15.983290222222225 | 166.82581797222224 | – | 7.980498432833332 | – | – | sourced | – | source |
| M4 (10-core GPU, 16 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 76.16243562222222 | 1091.1117940111112 | – | 1.1983527194666668 | – | – | sourced | – | source |
| M4 (10-core GPU, 16 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 8.726884422222223 | 83.05415 | – | 15.662719702777778 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085