Instructions to use runanywhere/Fara1.5-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use runanywhere/Fara1.5-4B-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 runanywhere/Fara1.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use runanywhere/Fara1.5-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "runanywhere/Fara1.5-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "runanywhere/Fara1.5-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Ollama
How to use runanywhere/Fara1.5-4B-GGUF with Ollama:
```
ollama run hf.co/runanywhere/Fara1.5-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use runanywhere/Fara1.5-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "runanywhere/Fara1.5-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use runanywhere/Fara1.5-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/runanywhere/Fara1.5-4B-GGUF:Q4_K_M
```

Lemonade

How to use runanywhere/Fara1.5-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Fara1.5-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use runanywhere/Fara1.5-4B-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 runanywhere/Fara1.5-4B-GGUF: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 runanywhere/Fara1.5-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use runanywhere/Fara1.5-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf runanywhere/Fara1.5-4B-GGUF: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 "runanywhere/Fara1.5-4B-GGUF: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"

Fara1.5-4B — GGUF (llama.cpp)

llama.cpp GGUF conversion of microsoft/Fara1.5-4B, Microsoft AI Frontiers' agentic Computer-Use Agent (CUA) for web browsers (Qwen3.5-VL arch, Qwen3_5ForConditionalGeneration). This repo only re-packages Microsoft's model for on-device inference — all capabilities and credit belong to Microsoft AI Frontiers. Original model, full system prompt, and MagenticLite agent scaffold: https://huggingface.co/microsoft/Fara1.5-4B and https://github.com/microsoft/fara.

Files

File	What	Size
`Fara1.5-4B-Q4_K_M.gguf`	text model, 4-bit (Q4_K_M)	~2.5 GB
`Fara1.5-4B-f16.gguf`	text model, full precision (f16)	~7.9 GB
`mmproj-Fara1.5-4B-f16.gguf`	vision projector (required for images)	~0.6 GB

A VLM needs both a text GGUF and the mmproj. llama.cpp maps the vision tower to PROJECTOR_TYPE_QWEN3VL and the text model to LLM_ARCH_QWEN3VL.

Conversion

Produced with a qwen3_5-aware llama.cpp convert_hf_to_gguf.py:

python convert_hf_to_gguf.py microsoft/Fara1.5-4B --outfile Fara1.5-4B-f16.gguf --outtype f16
python convert_hf_to_gguf.py microsoft/Fara1.5-4B --mmproj --outfile mmproj-Fara1.5-4B-f16.gguf
llama-quantize Fara1.5-4B-f16.gguf Fara1.5-4B-Q4_K_M.gguf Q4_K_M

Usage

llama-mtmd-cli -m Fara1.5-4B-Q4_K_M.gguf --mmproj mmproj-Fara1.5-4B-f16.gguf \
  --image screenshot.png -p "<FARA_SYSTEM_PROMPT> ... your task"

Fara is a web-browser agent. Use Microsoft's contract (see the base model):

Provide the full system prompt including the computer_use tool schema inside <tools></tools>.
The model emits <tool_call>{"name": "computer_use", "arguments": {...}}</tool_call>.
Coordinates are returned in a fixed 1000×1000 space; scale to your viewport (e.g. x*1.44, y*0.9 for a 1440×900 window). 1440×900 is the recommended capture size.

Validation

Verified running on Apple silicon through llama.cpp (CPU and Metal GPU). On real 1440×900 browser screenshots with Fara's exact CUA prompt, the Q4_K_M produced valid left_click tool-calls with correct coordinate grounding (matching an independent community Q4_K_M byte-for-byte on shared tasks, and matching the MLX 4-bit build).

License

MIT, inherited from microsoft/Fara1.5-4B. Review Microsoft's model card for intended use, limitations, and responsible-AI guidance (Fara pauses at safety-critical points; keep a human in the loop for irreversible actions).

Downloads last month: 80

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

16-bit

Model tree for runanywhere/Fara1.5-4B-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

microsoft/Fara1.5-4B

Quantized

(11)

this model