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 rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit21.5 tok/smeasured4,73819.5 GB131,072llama.cpp
RTX 3090 24GB4-bit37.9 tok/smeasured3,582- GB131,072llama.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.