community pool / model answer

AceReason-Nemotron-1.1-7B

chat · nvidia/AceReason-Nemotron-1.1-7B

63.6 tok/s · model median · 28 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit57.3 tok/smeasured1,248- GB131,072llama.cpp
RTX 3060 Ti 8GB4-bit68.1 tok/smeasured2,1376.7 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.