community pool / model answer

GLM-5.2-Abliterated-MXFP8-NVFP4-NF3-Hybrid

chat · jacklarmer/GLM-5.2-Abliterated-MXFP8-NVFP4-NF3-Hybrid

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell 96GB ×48-bit92 tok/sreported355- GB480,000vllm

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.