community pool / model answer

GLM-5.3-Flash-AWQ-W4A16

chat · wtdcode/GLM-5.3-Flash-AWQ-W4A16

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×84-bit75.2 tok/sreported358183.4 GB204,800vllm

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.