community pool / model answer

Hermes-3-Llama-3.1-8B

chat · NousResearch/Hermes-3-Llama-3.1-8B

38.5 tok/s · model median · 5 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GTX 1080 Ti 11GB4-bit53.1 tok/sreported-7.7 GB8,192llama.cpp
GTX 1080 Ti 11GB5-bit38.2 tok/sreported-8.4 GB8,192llama.cpp
Ryzen AI Max 395 128GB5-bit38.5 tok/smeasured-7.8 GB32,768llama.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.