M2 (8-core GPU, 8 GB)
2 records across 2 models (quants: Q4_K - Medium).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M2 (8-core GPU, 8 GB) | llama-3-1-8b-instruct | Q4_K - Medium | llamafile | 18.342969166666663 | 148.82072661111113 | – | 8.390452365666668 | – | – | sourced | – | source |
| M2 (8-core GPU, 8 GB) | llama-3-2-1b-instruct | Q4_K - Medium | llamafile | 34.48367238888889 | 523.2109411111111 | – | 2.7225200694166665 | – | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085