M2 Ultra (76-core GPU, 192 GB)
1 records across 1 models (quants: Q4_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 Ultra (76-core GPU, 192 GB) | Llama 2 7B | Q4_0 | llama.cpp | 94.27 | 1238.48 | – | – | 512 | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085