Instructions to use starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf starchicken/UI-Mate-27B-GGUF: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 starchicken/UI-Mate-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf starchicken/UI-Mate-27B-GGUF: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 starchicken/UI-Mate-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf starchicken/UI-Mate-27B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/starchicken/UI-Mate-27B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use starchicken/UI-Mate-27B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "starchicken/UI-Mate-27B-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": "starchicken/UI-Mate-27B-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/starchicken/UI-Mate-27B-GGUF:Q4_K_M

Ollama
How to use starchicken/UI-Mate-27B-GGUF with Ollama:
```
ollama run hf.co/starchicken/UI-Mate-27B-GGUF:Q4_K_M
```

Unsloth Studio

How to use starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for starchicken/UI-Mate-27B-GGUF to start chatting

How to use starchicken/UI-Mate-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf starchicken/UI-Mate-27B-GGUF: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": "starchicken/UI-Mate-27B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use starchicken/UI-Mate-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/starchicken/UI-Mate-27B-GGUF:Q4_K_M
```

Lemonade

How to use starchicken/UI-Mate-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull starchicken/UI-Mate-27B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.UI-Mate-27B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-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 starchicken/UI-Mate-27B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use starchicken/UI-Mate-27B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf starchicken/UI-Mate-27B-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 "starchicken/UI-Mate-27B-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"

UI-Mate-27B GGUF

Community GGUF quantization of Tencent/UI-Mate-27B — an open-weight foundation GUI agent based on Qwen3.6-27B. It observes live screenshots, reasons over the visible state, and produces structured keyboard/mouse actions for native desktop interaction (pyautogui-compatible).

Converted with llama.cpp b10437 (convert_hf_to_gguf.py --no-nextn), quantized with llama-quantize (CUDA). The vision projector (mmproj) is included.

Files

File	Size	Notes
`UI-Mate-27B-Q4_K_M.gguf`	15.4 GB	Recommended for 24 GB GPUs (RTX 3090/4090)
`UI-Mate-27B-Q5_K_M.gguf`	17.9 GB	Middle ground; 24 GB GPUs
`UI-Mate-27B-Q6_K.gguf`	20.6 GB	Highest fidelity; needs 24 GB+ with modest context
`mmproj-UI-Mate-27B-F16.gguf`	0.86 GB	Vision projector — required for image input

Usage (llama.cpp)

Requires llama.cpp b10437+ (qwen3_5 / Gated DeltaNet support).

llama-server \
  -m UI-Mate-27B-Q4_K_M.gguf \
  --mmproj mmproj-UI-Mate-27B-F16.gguf \
  --ctx-size 65536 \
  --n-gpu-layers 999 \
  --image-min-tokens 1024 \
  --n-predict 8192

Works with any OpenAI-compatible client (llama.cpp server, llama-swap, LM Studio, etc.). For full GUI-agent behavior (structured actions, coordinate rescaling, demonstration-guided mode), use Tencent's UI-Mate harness against the endpoint.

Benchmarks (RTX 3090, CUDA, ngl 999)

Metric	Q4_K_M
pp512	1341 t/s
tg128	42.3 t/s
VRAM (Q4_K_M + mmproj, 64K ctx)	~19.7 GB

Perplexity (wikitext-2, 10K tokens, ctx 512)

Quant	PPL
Q4_K_M	6.5171 ± 0.216
Q5_K_M	6.4924 ± 0.216
Q6_K	6.4663 ± 0.214

Monotonic improvement with precision; Q6 is ~0.05 PPL better than Q4 — quantization loss is minimal.

Community Validation (llama.cpp / llama-swap)

Tested with Tencent's official UI-Mate harness against a llama.cpp b10437 server (llama-swap) on an RTX 3090 (24 GB).

Compatibility: llama.cpp accepts the harness's chat_template_kwargs.enable_thinking; the model emits both content (XML actions) and reasoning_content.
Single-step (5/5): all bundled examples produced valid <action> + <tool_call> output (e.g., Chrome bookmark → Ctrl+D hotkey; LibreOffice → File menu; Thunderbird → app icon).
Replay (5 steps): 2/5 exact match to recorded actions, 4/5 within 1–2 px.
Multi-turn: screenshot history + collapsing work correctly.

Note: Q4_K_M validated on 24 GB. Q6_K is provided for 24 GB+ GPUs (not GPU-validated on 24 GB).

Model Details (from the official card)

Parameters: 27B
Base model: Qwen3.6-27B
Input: task instruction, screenshots, interaction history, and optional demonstration context
Output: reasoning, a concise action description, and structured computer-use tool calls
Action space: mouse, keyboard, scrolling, waiting, user interaction, and task completion
Training: supervised fine-tuning followed by online reinforcement learning in executable GUI environments
License: Apache-2.0

UI-Mate supports two complementary modes:

General computer use: execute tasks from natural-language instructions and live screenshots.
Demonstration-guided computer use: adapt a reusable workflow extracted from one successful demonstration to a new task.

Evaluation (from the official card)

Instruction-only execution

Benchmark	UI-Mate-27B
OSWorld-Verified · average score	77.0
WindowsAgentArena · average score	66.2
OSWorkerBench · strict success	41.00
OSWorkerBench · progress	76.86

Demonstration-guided execution (OSWorkerBench-Subset, 33 tasks)

Metric	Instruction only	+ one demonstration
strict success	17.17	35.35 (+18.18 pp)
progress	67.85	81.14 (+13.29 pp)

Intended Use and Limitations

UI-Mate-27B is intended for research and development of screenshot-based GUI agents in controlled desktop environments. Its behavior can be affected by application versions, screen layouts, display scaling, latency, and unexpected UI state. Benchmark performance does not guarantee reliable execution in arbitrary environments, and the model requires an external runtime to execute its predicted actions.

Safety

Computer-use agents can make mistakes, encounter prompt injection, or trigger consequential actions.

Prefer isolated or disposable environments.
Avoid unattended, high-stakes, or destructive workflows.
Require human confirmation before sensitive operations.
Monitor the interaction trajectory and verify the resulting application state.
Do not treat a model-reported success as proof that the intended outcome was achieved.

Notes

Architecture: qwen35 (Qwen3.5-family Gated DeltaNet hybrid), 64 layers, hidden 5120, native 262K context. MTP head excluded from this conversion (--no-nextn).
Reasoning model: responses include reasoning_content before the final answer — set a generous max_tokens (e.g. 8192) for long-horizon tasks.
Grounding: --image-min-tokens 1024 is recommended for GUI grounding accuracy (llama.cpp warning for Qwen-VL models).
Original model: Apache-2.0. Third-party components retain their licenses.

Credits

Model: Tencent HY Frontier (UI-Mate) — repo · project page
Base: Qwen/Qwen3.6-27B
Quantization: llama.cpp b10437 (official toolchain)

Citation

@article{uimate2026,
  title   = {UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations},
  author  = {{Tencent HY Frontier Multimodal Agent Team}},
  journal = {arXiv preprint},
  year    = {2026}
}

Downloads last month: 120

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

Model tree for starchicken/UI-Mate-27B-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

tencent/UI-Mate-27B

Quantized

(4)

this model