community pool / model answer
DeepHermes-3-Mistral-24B-Preview
chat · NousResearch/DeepHermes-3-Mistral-24B-Preview
30.8 tok/s · model median · 31 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 21.5 tok/s | measured | 4,738 | 19.5 GB | 131,072 | llama.cpp |
| RTX 3090 24GB | 4-bit | 37.9 tok/s | measured | 3,582 | - GB | 131,072 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.