Instructions to use unsloth/Qwen3-VL-30B-A3B-Instruct-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 unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3-VL-30B-A3B-Instruct-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": "unsloth/Qwen3-VL-30B-A3B-Instruct-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/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF to start chatting

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-VL-30B-A3B-Instruct-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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/Qwen3-VL-30B-A3B-Instruct-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"

Missing vision parameters?

by mojmir144 - opened Nov 7, 2025

Discussion

mojmir144

Nov 7, 2025

•

edited Nov 7, 2025

Using ollama/ollama:0.12.9 (the same on ollama/ollama:0.12.10) docker image and loading Qwen3-VL-30B-A3B-Instruct-Q5_K_M.gguf got this error:

time=2025-11-07T06:33:31.230Z level=DEBUG source=ggml.go:276 msg="key with type not found" key=qwen3vlmoe.vision.image_mean default="&{size:0 values:[0.5 0.5 0.5]}"
time=2025-11-07T06:33:31.231Z level=DEBUG source=ggml.go:276 msg="key with type not found" key=qwen3vlmoe.vision.image_std default="&{size:0 values:[0.5 0.5 0.5]}"
time=2025-11-07T06:33:31.742Z level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:35594: runtime error: invalid memory address or nil pointer dereference\ngoroutine 5 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x558f290dcee0?, 0x558f29a403e0?})\n\truntime/panic.go:787 +0x132\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel.func1()\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1137 +0x11a\npanic({0x558f290dcee0?, 0x558f29a403e0?})\n\truntime/panic.go:787 +0x132\ngithub.com/ollama/ollama/ml/nn.(*Conv3D).Forward(0x0, {0x558f2924f6d0, 0xc0009de400}, {0x558f29259aa0?, 0xc0009e0018?}, 0x101018f29affe80?, 0x7fb4c04d21c8?, 0x7fb5099465c0?, 0x10?, 0x0, ...)\n\tgithub.com/ollama/ollama/ml/nn/convolution.go:25 +0x3a\ngithub.com/ollama/ollama/model/models/qwen3vl.(*VisionModel).Forward(0xc0004c80c0, {0x558f2924f6d0, 0xc0009de400}, {0x558f29259aa0, 0xc0009e0000}, 0xc000d5f950)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model_vision.go:223 +0x118\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc0005e9a00, {0x558f2924f6d0, 0xc0009de400}, {0xc001ad0000, 0x400436, 0x700000})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:43 +0x14e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0xc0004ee3c0, 0x1)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1048 +0x34e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0004ee3c0, {0x7ffe5920edb9?, 0x558f2802903a?}, {0x0, 0x2, {0xc00041ee80, 0x1, 0x1}, 0x1}, {0x0, ...}, ...)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1170 +0x2b1\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0004ee3c0, {0x558f29242948, 0xc0001c70a0}, 0xc00044e000)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1249 +0x54d\nnet/http.HandlerFunc.ServeHTTP(0xc0004c98c0?, {0x558f29242948?, 0xc0001c70a0?}, 0xc0000b9b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x558f27cd9f65?, {0x558f29242948, 0xc0001c70a0}, 0xc00044e000)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x558f2923ef50?}, {0x558f29242948?, 0xc0001c70a0?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc0000a8000, {0x558f29244cd8, 0xc0005ea870})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485"
time=2025-11-07T06:33:31.743Z level=INFO source=runner.go:1222 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:false KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-07T06:33:31.743Z level=INFO source=sched.go:446 msg="Load failed" model=/root/.ollama/models/blobs/sha256-48d36eda5b82f50fea3d27a2a3963fa6b87e41411c7f503db06074c39f686a79 error="do load request: Post \"http://127.0.0.1:38459/load\": EOF"
time=2025-11-07T06:33:31.743Z level=DEBUG source=server.go:1699 msg="stopping llama server" pid=52
time=2025-11-07T06:33:31.743Z level=DEBUG source=server.go:1705 msg="waiting for llama server to exit" pid=52
time=2025-11-07T06:33:31.773Z level=ERROR source=server.go:273 msg="llama runner terminated" error="signal: killed"
time=2025-11-07T06:33:31.773Z level=DEBUG source=server.go:1709 msg="llama server stopped" pid=52

Any suggestions to run it inside docker?

danielhanchen

Unsloth AI org Dec 10, 2025

You're using ollama. As we have a separate mmproj file, ollama doesn't detect it.

You will need to use something like llama.cpp.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment