- Model
- https://huggingface.co/deepcogito/cogito-v2-preview-deepseek-671B-MoE
- Author
- deepcogito (org)
- Likes
- 36
- Downloads (30 days)
- 265
- Task
- text-generation
- Library
- transformers
- License
- mit
- Parameters
- 671B
- Gated
- No
- Created
- 2025-07-27
- Last modified
- 2025-07-31
- Base models
- deepseek-ai/DeepSeek-V3-Base
- Snapshot
- 2026-10-29
Run it locally.
Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.
llama.cpp
llama-cli -hf deepcogito/cogito-v2-preview-deepseek-671B-MoE Ollama
ollama run hf.co/deepcogito/cogito-v2-preview-deepseek-671B-MoE These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.
ShadowCode prompt.
Paste this into ShadowCode after you open Settings › Local models.
In Settings › Local models, run deepcogito/cogito-v2-preview-deepseek-671B-MoE only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading. Download Shadowfetch Linux — ISO, checksum and signature.