Instructions to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 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 aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

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 aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

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 aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

Use Docker

docker model run hf.co/aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

LM Studio
Jan

vLLM

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aogavrilov/diffusiongemma-agent-iq3-cuda13"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aogavrilov/diffusiongemma-agent-iq3-cuda13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

Ollama
How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with Ollama:
```
ollama run hf.co/aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
```

Unsloth Studio

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 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 aogavrilov/diffusiongemma-agent-iq3-cuda13 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 aogavrilov/diffusiongemma-agent-iq3-cuda13 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aogavrilov/diffusiongemma-agent-iq3-cuda13 to start chatting

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

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": "aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

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 aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

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 "aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M" \
  --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 aogavrilov/diffusiongemma-agent-iq3-cuda13 with Docker Model Runner:
```
docker model run hf.co/aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M
```

Lemonade

How to use aogavrilov/diffusiongemma-agent-iq3-cuda13 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aogavrilov/diffusiongemma-agent-iq3-cuda13:Q4_K_M

Run and chat with the model

lemonade run user.diffusiongemma-agent-iq3-cuda13-Q4_K_M

List all available models

lemonade list

diffusiongemma-agent-iq3-cuda13 / payload /app /docs /qwen_code_local.md

aogavrilov

Add files using upload-large-folder tool

ef2127a verified 16 days ago

preview code

Raw

History Blame Contribute Delete

2.61 kB

Qwen Code Local Wrapper

Qwen Code is an upstream open-source terminal agent connected to the local DiffusionGemma GPU gateway. It is an inspection-only companion to the primary Aider edit workflow.

Verified Runtime

Qwen Code: 0.19.10
Node: .tools/node-v22.17.1-win-x64/node.exe
WSL/Git Bash gateway: http://127.0.0.1:4100/v1
WSL/Git Bash model: diffusiongemma-local
WSL/Git Bash MCP: diffusiongemma-local-agent, repomix, serena
native Windows fallback gateway: http://127.0.0.1:8090/v1
native Windows fallback model: diffusiongemma-26b-a4b-it-iq4xs-aider-local
mode: read-only inspection

The local Node 22 runtime is intentional. The system Node 24 causes an upstream Qwen/libuv shutdown assertion on this host. The wrapper does not modify the global Node installation.

Usage

Start the GPU backend and gateway first:

.\scripts\start_agent_gateway.ps1

Inspect an explicitly named file from PowerShell through the native read-only fallback:

.\scripts\run_qwen_code_windows.ps1 --repo C:\path\to\repo -- --output-format json --prompt "Read src\app.py. Summarize the request flow."

The unified entrypoint maps Git Bash/MSYS and WSL calls to the MCP-enabled runner. Native PowerShell uses the read-only fallback:

python scripts\dg_agent.py qwen-code -- --repo C:\path\to\repo -- --prompt "Read src\app.py. State the error handling path."

From WSL, use a repository below /mnt/<drive>/... so the wrapper can map it back to the Windows runner:

scripts/dg_agent.sh qwen-code -- --repo /mnt/c/path/to/repo -- \
  --prompt "Read src/app.py. State the error handling path."

Use prompts that name the file to inspect. The safe proxy offers the matching file through a bounded read_file tool call for the native Windows fallback. The WSL/Git Bash runner mounts diffusiongemma-local-agent, repomix, and serena from qwen-code.mcp.json. Qwen edit requests are still not the reliable path on this model; run Aider for any modification:

wsl.exe --exec bash -lc 'cd /mnt/c/path/to/repo && /mnt/c/Users/alexg/Downloads/diffusiongemma-agent/scripts/run_aider_local.sh --repo "$PWD" --message "..."'

Verification

.\scripts\run_qwen_code_windows.ps1 --help-local
wsl.exe --exec bash -lc 'cd /mnt/c/Users/alexg/Downloads/diffusiongemma-agent && ./scripts/dg_agent.sh smoke --suite qwen-code --timeout 60'

The live smoke verifies the native runner and the local GPU gateway. A verified read-only probe against calc.py returned a - b without changing the target repository.