community pool / model answer

AceReason-Nemotron-1.1-7B-GGUF

chat · lmstudio-community/AceReason-Nemotron-1.1-7B-GGUF

59.7 tok/s · model median · 8 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit59.7 tok/smeasured2,5637.3 GB131,072llama.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.