DeepSeek-V4.1-Flash-MTPLX-streaming-q2
OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2Content controls: not assessed.
Model from Hugging Face for text generation: OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 · mlx
Datos del modelo
DeepSeek-V4.1-Flash-MTPLX-streaming-q2 is an open-weights language model for text generation. The primary file is experts.bin (169.87 GB). The primary file needs about 204 GB free for the selected file. License: MIT. The SHA-256 prefix is dd847019755c. The primary Download is available now. No tested run commands for this file yet. See Files for current download availability. The size and hash details refer to the selected file, not every file in the repository. The memory figure is estimated from recorded file size with working room included. The size line uses recorded file bytes when they are present in this model record.
Qué incluye
62 hosted of 75 listed
Acerca de este modelo
External Hugging Face catalog record for OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2. Task: text generation. Library: mlx. Base model: deepseek-ai/DeepSeek-V4.1-Flash. Popularity signal at import: 2,176 downloads and 3 likes.
Datos básicos
- Hosted here
- 62 hosted of 75 listed
- Full repo upstream
- 404 GB
- Recommended file
- 169.9 GB · experts.bin
- Format
- BIN · safetensors
- Downloads on Hugging Face
- 2,176
- File hashes
- Hashes recorded. Date not recorded.
Licencia y origen
License: mit
Check the license text and keep the required notices when you use or share the files.
Upstream source →- Task
- text generation
- Hosted here
- 62 files, 404 GB
- Full repo upstream
- 404 GB
- Recommended file
- 169.9 GB · experts.bin
- Files
- 62 hosted of 75 listed
- Download
- Download here (62 hosted files)
- Added to Hugging Bay
- Updated at source
FAQ
What is this model?
OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 is an open-weights language model for text generation published by OpensourceWTF, added to Hugging Bay Sep 22, 2026. Model from Hugging Face for text generation: OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 · mlx
Can I use it commercially?
It is released under the mit license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.
How big is it?
Hosted here: 62 files, 404 GB. Full repo upstream: 404 GB. The recommended download, experts.bin, is 169.9 GB.
What can I download here?
Hosted here: 62 files, 404 GB. Full repo upstream: 404 GB. The original release is at https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2.
File checks and computer fit
File pattern scans
Automated file-pattern scans flagged nothing; not a safety guarantee. 62 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-opensourcewtf-deepseek-v4-1-flash-mtplx-streaming-q2/safety on Hugging Bay.
Will OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 run on my computer?
We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.
Repack of deepseek-ai/deepseek-v4.1-flash (from the publisher card on Hugging Face). This does not mean the files match the original weights.
2 other repacks declare the same base on their cards.