M4 (8-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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 (8-core GPU, 16 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 15.26954622222222 | 134.02995044444447 | – | 9.18359174066667 | – | – | sourced | – | source |
| M4 (8-core GPU, 16 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 65.86037953333333 | 897.0363834222222 | – | 1.4411192250444445 | – | – | sourced | – | source |
| M4 (8-core GPU, 16 GB) | qwen-2-5-14b-instruct | Q4_K - Medium | llamafile | 7.234274277777778 | 61.06916633333333 | – | 20.47596530788889 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085