community pool / model answer

GLM-5.2-GGUF

chat · unsloth/GLM-5.2-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell 96GB ×44-bit39.7 tok/sreported4,003348.6 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.