Qwen3.8-2.4T-A95B
Qwen3.8-2.4T-A95B is an open-weight language model from Alibaba Qwen, released on August 12, 2026.
- Developer
- Alibaba Qwen
- Released
- August 12, 2026
- Total parameters
- 2.4T
- Active parameters per token
- 95B
- Architecture
- MoE
- Context window
- 256K
- Input
- Text
- License
- Qwen3.8-Max License
- Commercial use
- Yes, with conditions
- Official weights, GB
- 4,892.4 GB
- Hugging Face repository
- huggingface.co
- Checked on
Qwen3.8-2.4T-A95B is a mixture-of-experts model with 2.4T total parameters, of which 95B are active for each token. Alibaba Qwen lists a context window of 262,144 tokens natively, extensible to about 1M. The model takes text input.
The weights are released under the Qwen3.8-Max License. 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. Model-as-a-service and AI work assistant businesses with more than US$50 million in group revenue over 12 months need a separate license from Qwen. Internal use is exempt.
The official weights on Hugging Face take about 4,892 GB in BF16. 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
- 2,400B
- Active parameters, billions
- 95B
- 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. Model-as-a-service and AI work assistant businesses with more than US$50 million in group revenue over 12 months need a separate license from Qwen. Internal use is exempt.
- Weights precision
- BF16
- Official quantized or alternative versions
- Qwen/Qwen3.8-2.4T-A95B-FP8
- License text
- huggingface.co
- Sources
Page URL Hugging Face model card https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/raw/main/README.md License text on Hugging Face https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/raw/main/LICENSE Hugging Face API https://huggingface.co/api/models/Qwen/Qwen3.8-2.4T-A95B?expand=safetensors GitHub file https://raw.githubusercontent.com/QwenLM/Qwen3.5/main/README.md (news: 2026-08-12) qwen.ai announcement https://qwen.ai/blog?id=qwen3.8
Questions
What license does Qwen3.8-2.4T-A95B use?
Can I use Qwen3.8-2.4T-A95B commercially?
How much memory does Qwen3.8-2.4T-A95B need?
How many parameters does Qwen3.8-2.4T-A95B 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.