M4 (10-core GPU, 24 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, 24 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 15.935378370370373 | 148.96748985185187 | – | 8.236942598851853 | – | – | sourced | – | source |
| M4 (10-core GPU, 24 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 75.4330094074074 | 1035.9960293703705 | – | 1.2527001605185184 | – | – | sourced | – | source |
| M4 (10-core GPU, 24 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 9.238281555555554 | 93.30326355555556 | – | 13.714502268555552 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085