DeepSeek-V4.1-Flash-1017
DeepSeek-V4.1-Flash-1017 is an open-weight language model from DeepSeek, released on October 17, 2026. DeepSeek describes it as a minor update to DeepSeek-V4.1-Flash.
- Developer
- DeepSeek
- Released
- October 17, 2026
- Total parameters
- 763B
- Architecture
- MoE
- Context window
- 1M
- Input
- Text, image
- License
- MIT
- Commercial use
- Yes
- Official weights, GB
- 510.3 GB
- Hugging Face repository
- huggingface.co
- Checked on
DeepSeek-V4.1-Flash-1017 is a mixture-of-experts model with about 763B parameters in the Hugging Face metadata. DeepSeek lists a context window of 1M tokens. The model accepts text and image input. The weights are released under the MIT license, which allows commercial use.
The official weights on Hugging Face take about 510.3 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
- 763B
- Context window, tokens
- 1M
- License type
- MIT
- License conditions
- MIT: keep the copyright and permission notice.
- Weights precision
- Mixed FP8 + INT8 + BF16
- License text
- huggingface.co
- Sources
Page URL Hugging Face model page https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017 License text on Hugging Face https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE Hugging Face weights index https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/raw/main/model.safetensors.index.json
Questions
What license does DeepSeek-V4.1-Flash-1017 use?
Can I use DeepSeek-V4.1-Flash-1017 commercially?
How much memory does DeepSeek-V4.1-Flash-1017 need?
What context window does DeepSeek-V4.1-Flash-1017 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.