community pool / model answer

NVIDIA-Nemotron-3-Nano-4B-GGUF

chat · nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF

184 tok/s · model median · 4 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5070 12GB4-bit182.2 tok/smeasured1244.6 GB32,768llama.cpp
RTX 5090 32GB8-bit237.8 tok/sreported34- GB2,048lmstudio

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.