community pool / model answer

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

chat · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

285.6 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 + RTX 2080 20GB4-bit117 tok/sreported-17 GB2,048llama.cpp
RTX 5090 32GB4-bit299.4 tok/sreported12321.7 GB8,192llama.cpp, ollama

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.