community pool / model answer

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

chat · lmstudio-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Max 128GB4-bit113.7 tok/sreported19- GB8,192llama.cpp
RTX 5090 32GB4-bit274.4 tok/sreported32- 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.