community pool / model answer

Qwen3.8-27B-W4A16-AutoRound

chat · dbirks/Qwen3.8-27B-W4A16-AutoRound

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×24-bit182.4 tok/smeasured82544.4 GB262,144sglang, vllm

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.