Qwen3.8-27B Gets INT4 and MXFP4 Quantized Releases
Qwen3.8-27B now offers INT4 and MXFP4 quantized versions on Hugging Face; the INT4 AutoRound build is about 18GB and supports working MTP speculative decoding, aiming to cut deployment costs and boost inference efficiency.
2026-08-16 ~ 2026-08-17 · 2 related posts
- Episode 1: Alibaba's Open-Source Qwen 3.8 27B Draws Rave Local Reviews, Nears Claude Opus(2026-08-15, 6 posts)
- Episode 2: Alibaba Open-Sources Qwen3.8-27B Multimodal Model That Runs on a Single GPU(2026-08-15, 2 posts)
- Episode 3: Uncensored Qwen3.8-27B GGUF variants dominate Hugging Face trending(2026-08-15, 6 posts)
- Episode 4: Qwen3.8-27B Gets INT4 and MXFP4 Quantized Releases(2026-08-16, 2 posts)
- Qwen3.8-27B-int4-AutoRound (18GB) with working MTP spec decode — BusinessMud9586 · 2026-08-16
- Qwen3.8-27B INT4 and MXFP4 Quantized Models Released — HaihaoShen · 2026-08-17