M1 Pro (16-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 (16-core GPU, 16 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 21.88205522222222 | 204.5403022222222 | – | 6.089909109518518 | – | – | sourced | – | source |
| M1 Pro (16-core GPU, 16 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 78.15808337037036 | 1158.147661425926 | – | 1.0274150409074074 | – | – | sourced | – | source |
| M1 Pro (16-core GPU, 16 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 11.90798088888889 | 106.6591231111111 | – | 11.83519856488889 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085