Qwen3.6 27B AWQ 4 bit (compressed tensors) Compressed tensors output of GPTQ calibration of Qwen3.6 27B with thinking + vision preserved. Which variant should I download? Stack Recommended Why SGLang + ROCm Native AWQ Faster on the fused Triton AWQ GEMM than the ROCm CT MoE path SGLang + NVIDIA Native AWQ Avoids the same Qwen3 5Moe CT loader bug seen on 35B (not yet confirmed on 27B but same code path) vLLM / autoawq / TGI on NVIDIA Either works CT loaders in those engines handle the gate correctly Inspection / re conversion This (CT) Raw GPTQ output from llmcompressor before AWQ repack Model Details Base model Qwen/Qwen3.6 27B Architecture Qwen3.5 dense+DeltaNet hybrid + vision tower Parameters 27B Format compressed tensors pack quantized (W4A16, group size=128) Calibration GPTQ via llmcompressor, 256 samples × 1024 tokens, thinking vision recipe For ignore list and benchmark numbers see the native variant's README. Convert to native AWQ Hardware origin Calibrated on 2× AMD Radeon AI PRO R9700 (gfx1201, RDNA4) with ROCm 7.2 + SGLang v0.5.10 + RDNA4 patches.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy