community pool / model answer

Llama-3.1-Nemotron-70B-Instruct-HF

chat · nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

5.2 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Ryzen AI Max 395 128GB4-bit5.2 tok/sreported-- GB16,384llama.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.