community pool / model answer

Qwen3.8-27B-Uncensored-int4-AutoRound

chat · johannrplaster/Qwen3.8-27B-Uncensored-int4-AutoRound

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB4-bit97.8 tok/sreported356- 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.