Qwen/Qwen3.6-27B
Qwen3.6 dense multimodal model (27B) with gated delta networks hybrid attention, MTP, and 262K context
Qwen3.6 flagship dense — single-GPU FP8 or 2x GPU BF16
Qwen3.6 dense multimodal model (27B) with gated delta networks hybrid attention, MTP, and 262K context
Qwen3.6 flagship dense — single-GPU FP8 or 2x GPU BF16
View on HuggingFace
View on ModelScope