DeepHermes-3-Llama-3-8B-Preview
4 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Pro | DeepHermes-3-Llama-3-8B-Preview | 4bit | oMLX | 55.0 | 1393.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Pro | DeepHermes-3-Llama-3-8B-Preview | 4bit | oMLX | 53.4 | 1374.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Pro | DeepHermes-3-Llama-3-8B-Preview | 4bit | oMLX | 41.2 | 1205.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M5 Pro | DeepHermes-3-Llama-3-8B-Preview | 4bit | oMLX | 37.2 | 1127.0 | – | – | 16384 | 2026-10-07 | community | – | source |