community pool / model answer

Qwen3.8-27B-AWQ-MTP

chat · shawnw3i/Qwen3.8-27B-AWQ-MTP

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
A100 40GB4-bit87.1 tok/sreported40031 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.