community pool / model answer

GLM-5.3-Flash-W4A16-MTP

chat · canada-quant/GLM-5.3-Flash-W4A16-MTP

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
CMP 170HX 64GB ×44-bit153.1 tok/sreported157- GB131,072vllm

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.