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 Aug 1, 2025

Commit

9ce37dd

verified ·

1 Parent(s): 036335c

Upload folder using huggingface_hub

Browse files

Files changed (17) hide show

.gitattributes +16 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00001-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00002-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00003-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00004-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00005-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00006-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00007-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00008-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00009-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00010-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00011-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00012-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00013-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00014-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00015-of-00016.gguf +3 -0
UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00016-of-00016.gguf +3 -0

@@ -208,3 +208,19 @@ UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00009-of-00012.gguf fi
 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00010-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00011-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00012-of-00012.gguf filter=lfs diff=lfs merge=lfs -text

 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00010-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00011-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
 UD-Q6_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q6_K_XL-00012-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00001-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00002-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00003-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00004-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00005-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00006-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00007-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00008-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00009-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00010-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00011-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00012-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00013-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+UD-Q8_K_XL/cogito-v2-preview-deepseek-671B-MoE-UD-Q8_K_XL-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8538284f98176d1e01eb2b1abfa32ba0b28ac2a3278697c6cade650a6ffcf5
+size 49322757760

+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7725d3b8a670580c2b40cce8c59659e944a9abd2eb1396cef966c9bc5a468b
+size 46861187328

+version https://git-lfs.github.com/spec/v1
+oid sha256:7df67d94edaa83f2abe4b4144ce9612f23155f2883f4baca933698b102a637f2
+size 47846644512

+version https://git-lfs.github.com/spec/v1
+oid sha256:af79b98e875dc963693b8be49268853153d55ce5827934cc63055296fccebaaa
+size 49045693120

+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac9ea0249387360326d3b709c547e571086c6165979ab7e3e9eecacfc50aec5
+size 47353915936

+version https://git-lfs.github.com/spec/v1
+oid sha256:5080e3d8178c138bb0ad8e407f817ff164e3cf853ed5445ec7afc91167a9cb3e
+size 49670713888

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

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

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

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