community pool / model answer

Qwen3.8-27B-GPTQ-W4A16

chat · pearsonkyle/Qwen3.8-27B-GPTQ-W4A16

132.7 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit132.7 tok/smeasured-- 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.