Instructions to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Ollama:
```
ollama run hf.co/unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF to start chatting

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.cogito-v2-preview-deepseek-671B-MoE-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default unsloth/cogito-v2-preview-deepseek-671B-MoE-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

danielhanchen commited on Jul 31, 2025

Commit

705a00b

verified ·

1 Parent(s): d367cd1

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

.gitattributes +6 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00001-of-00006.gguf +3 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00002-of-00006.gguf +3 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00003-of-00006.gguf +3 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00004-of-00006.gguf +3 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00005-of-00006.gguf +3 -0
Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00006-of-00006.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -180,3 +180,9 @@ Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00005-of-00008.gguf filter=lfs dif
 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text

 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
 Q4_0/cogito-v2-preview-deepseek-671B-MoE-Q4_0-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00001-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91000753b620304f3f12e9897afa785d36a60525d1f1b003cdd4c95cba8196c2
+size 49940160832

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00002-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4104f5ef30f0724d0812d818286cc94d870996fb02eded248f62b1165b8d69
+size 49617660448

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00003-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e40aa88a42ad7195de94cf6d5b9119d214b22b73981e29b1328f415481727b96
+size 49617660448

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00004-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:10d9071ce450d871b9b5e4a5bc9384dcbe3f7d9975e77bc7b9d2d7d24d794d63
+size 49617660448

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00005-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4459a2e65fbdae1800f6f423536f8b90454d0804e47d46e4220790e602d625
+size 49617660448

Q3_K_S/cogito-v2-preview-deepseek-671B-MoE-Q3_K_S-00006-of-00006.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:41f1d54d781072304714e2ab0c38014727153364318acfe1574f99947b8cc904
+size 41315243424