M2 Ultra (60-core GPU, 192 GB)
1 records across 1 models (quants: Q4_K - Medium).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Ultra (60-core GPU, 192 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 169.76082655555555 | 3272.209784333334 | – | 0.3388111018888889 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085