M2 (8 GPU)
2 records across 1 models (quants: Q4_0, Q8_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 (8 GPU) | llama 7B | Q4_0 | llama.cpp (Metal) | 21.7 | 145.91 | – | – | – | 2023-11-22 | community | – | source |
| M2 (8 GPU) | llama 7B | Q8_0 | llama.cpp (Metal) | 12.18 | 147.27 | – | – | – | 2023-11-22 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085