community pool / model answer

mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF

chat · bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF

21.8 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit21.8 tok/sreported-17.4 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.