Qwen3.8-27B-FP8 quantized model published on Hugging Face
Alibaba published an FP8 quantized version of Qwen3.8-27B on Hugging Face. The model is image-text-to-text, conversational, and Apache-2.0 licensed.
First seen 12 Aug, 16:21 UTC on OpenRouter6 sourcesLast update 38d ago
AlibabaLaunch · 12 Aug
Qwen 3.8 27B
New-generation model
$0.42 / $3.00per M tokens, in / out
262Kcontext
Openweights
What the sources say
Linked, never rewritten. Official means the lab itself.
How it unfolded
Every source in the order it appeared. Times in UTC.
12 Aug 16:21OpenRouter Qwen: Qwen3.8 2.4T A95B listed on OpenRouter13 Aug 08:01Hugging Face · Qwen Qwen/Qwen3.8-27B-FP8 published on Hugging Face14 Aug 15:00Hacker News Qwen 3.8 27B14 Aug 15:55OpenRouter Qwen: Qwen3.8 27B listed on OpenRouter14 Aug 17:01The Decoder Alibaba's Qwen team releases Qwen 3.8 models with open weights under the Apache 2.0 license16 Aug 23:45Hacker News Qwen 3.8 27B is excellent, but it defaults to overthinking things