Qwen3.8-27B is now available on Hugging Face

Alibaba's Qwen team released Qwen3.8-27B, a 28-billion-parameter image-text-to-text model, on Hugging Face, with an FP8 quantized version also available. The model is part of the Qwen3.8 collection, which includes the 2.4-trillion-parameter Qwen3.8-2.4T-A95B and its FP8 variant, all updated within the past two days.

Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up Qwen 's Collections Qwen3.8 Qwen-AgentWorld Qwen-Image-Bench WebWorld Qwen-Scope Qwen3.6 Qwen3.5 Qwen3-Coder-Next Qwen3-ASR Qwen3-TTS Qwen3-VL-Reranker Qwen3-VL-Embedding Qwen3-VL Qwen3Guard Qwen3-Omni Qwen3-Next Qwen-Image Qwen3-Coder Qwen3 Qwen3-Reranker Qwen3-Embedding WorldPM Qwen2.5-Omni Qwen2.5-VL Qwen2.5-1M QVQ QwQ Qwen2.5-Coder Qwen2.5-Math Qwen2.5 Qwen2-VL Qwen2-Audio Qwen2-Math Qwen2 Qwen1.5 Qwen Qwen3.8 updated 1 day ago Upvote 127 +117 Sort: Collection Qwen/Qwen3.8-2.4T-A95B Text Generation • 2.4T • Updated 2 days ago • 3.83k • • 883 Qwen/Qwen3.8-2.4T-A95B-FP8 Text Generation • 2.4T • Updated 2 days ago • 9.33k • 178 Qwen/Qwen3.8-27B Image-Text-to-Text • 28B • Updated 14 minutes ago • 2 • 7.99k Qwen/Qwen3.8-27B-FP8 Image-Text-to-Text • 28B • Updated 29 minutes ago • 73 Upvote 127 +123 Sort: Collection Share collection View history Collection guide Browse collections