community pool / model answer

OpenReasoning-Nemotron-32B-GGUF

chat · lmstudio-community/OpenReasoning-Nemotron-32B-GGUF

18.2 tok/s · model median · 12 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit15.4 tok/smeasured-2.5 GB16,384llama.cpp
RTX 3090 24GB4-bit22.1 tok/smeasured-- GB65,536llama.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.