Qwen3.8-Flash-Next
Qwen3.8-Flash-Next is an open-weight language model from Alibaba Qwen, released on August 26, 2026.
- Developer
- Alibaba Qwen
- Released
- August 26, 2026
- Total parameters
- 125B
- Active parameters per token
- 6B
- Architecture
- MoE
- Context window
- 256K
- Input
- Text, image
- License
- Qwen Community License 1.0
- Commercial use
- Yes, with conditions
- Official weights, GB
- 360 GB
- Hugging Face repository
- huggingface.co
- Checked on
Qwen3.8-Flash-Next is a mixture-of-experts model with 125B total parameters, of which 6B are active for each token. Qwen lists another 51B parameters of n-gram embeddings and 4B for multi-token prediction on top of that figure. Alibaba Qwen lists a context window of 262,144 tokens natively, extensible to about 1M. The model accepts text and image input.
The weights are released under the Qwen Community License 1.0. Commercial use is allowed with conditions. Products with more than 100 million monthly active users or more than US$20 million in monthly revenue must display the model name. Any model-as-a-service or AI work assistant business needs a separate license from Qwen before commercial use, whatever its revenue. Internal use is exempt.
The official weights on Hugging Face take about 360 GB. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.
- Total parameters, billions
- 125B
- Active parameters, billions
- 6B
- Context window, tokens
- 262.14K
- License type
- Custom license
- License conditions
- Products with more than 100 million monthly active users or more than US$20 million in monthly revenue must display the model name. Any model-as-a-service or AI work assistant business needs a separate license from Qwen before commercial use, whatever its revenue. Internal use is exempt.
- Official quantized or alternative versions
- Qwen/Qwen3.8-Flash-Next-FP8
- License text
- huggingface.co
- Sources
Page URL Hugging Face model card https://huggingface.co/Qwen/Qwen3.8-Flash-Next/raw/main/README.md License text on Hugging Face https://huggingface.co/Qwen/Qwen3.8-Flash-Next/raw/main/LICENSE Hugging Face weights index https://huggingface.co/Qwen/Qwen3.8-Flash-Next/raw/main/model.safetensors.index.json GitHub file https://raw.githubusercontent.com/QwenLM/Qwen3.8-Flash-Next/main/README.md (news: 2026-08-26)
Questions
What license does Qwen3.8-Flash-Next use?
Can I use Qwen3.8-Flash-Next commercially?
How much memory does Qwen3.8-Flash-Next need?
How many parameters does Qwen3.8-Flash-Next have?
Sources
Every figure comes from the developer’s model card, license text and official announcements, and from the model’s Hugging Face repository metadata. Each model page lists its sources and the date they were checked; the register is rechecked every week.