community pool / model answer

GLM-4.7-Flash-AWQ

chat · QuantTrio/GLM-4.7-Flash-AWQ

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit163.1 tok/sreported-- GB2,048vllm

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.