M4 Pro (20-core GPU, 48 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 Pro (20-core GPU, 48 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 32.67357938271605 | 361.8889191604938 | – | 3.435018682604938 | – | – | sourced | – | source |
| M4 Pro (20-core GPU, 48 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 118.8963297948718 | 2134.135712188034 | – | 0.5720378254615385 | – | – | sourced | – | source |
| M4 Pro (20-core GPU, 48 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 17.981375188034185 | 189.7956117692308 | – | 6.62966483617094 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085