Instructions to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF",
	filename="Qwen3-VL-30B-A3B-Instruct.Q4_K_H.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
# Run inference directly in the terminal:
llama cli -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
# Run inference directly in the terminal:
llama cli -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
# Run inference directly in the terminal:
./llama-cli -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

Use Docker

docker model run hf.co/steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

LM Studio
Jan
Ollama
How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
```

Unsloth Studio

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

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF to start chatting

How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

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": "steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

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 "steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF" \
  --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 steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF with Docker Model Runner:
```
docker model run hf.co/steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF
```

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.Qwen3-VL-30B-A3B-Instruct-MP-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Mixed Precision GGUF layer quantization of Qwen3-VL-30B-A3B-Instruct by Qwen

Original model: https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct

The hybrid quant employs different quantization levels on a per layer basis to enable both high performance and small file size at the same time. This particular quant was optimized for high performance across a set of test prompts with ~IQ4_XS size. The model shows occasional rep fails on test prompts when using greedy sampling, where the model goes into an infinite gen loop on a rep pattern. This problem could not be solved by adjusting layer quants so it appears to be baked into the model training. The 32B dense model (VL 32B) does not exhibit this failure mode.

The quants employed are all K to avoid slow CPU or older GPU processing of IQ quants. For this file the layer quants are as follows:

Q4_K_L : attn_v = q6_k attn_o = q6_k ffn_d = q6_k
Q5_K_L : attn_v = q8_0 attn_o = q6_k ffn_d = q6_k
Q6_K_S : Q6_K

LAYER_TYPES='[
   [0 ,"Q6_K_S"],[1 ,"Q5_K_S"],[2 ,"Q3_K_L"],[3 ,"Q3_K_M"],[4 ,"Q3_K_M"],[5 ,"Q3_K_M"],[6 ,"Q3_K_M"],[7 ,"Q3_K_M"],
   [8 ,"Q3_K_M"],[9 ,"Q3_K_M"],[10,"Q3_K_M"],[11,"Q3_K_M"],[12,"Q3_K_M"],[13,"Q3_K_M"],[14,"Q3_K_M"],[15,"Q3_K_M"],
   [16,"Q3_K_L"],[17,"Q3_K_M"],[18,"Q3_K_L"],[19,"Q3_K_M"],[20,"Q3_K_L"],[21,"Q3_K_M"],[22,"Q3_K_L"],[23,"Q3_K_M"],
   [24,"Q3_K_L"],[25,"Q3_K_L"],[26,"Q3_K_L"],[27,"Q3_K_L"],[28,"Q3_K_L"],[29,"Q3_K_L"],[30,"Q3_K_L"],[31,"Q3_K_L"],
   [32,"Q4_K_S"],[33,"Q4_K_S"],[34,"Q4_K_S"],[35,"Q4_K_S"],[36,"Q4_K_S"],[37,"Q4_K_S"],[38,"Q4_K_S"],[39,"Q4_K_S"],
   [40,"Q4_K_S"],[41,"Q4_K_S"],[42,"Q4_K_M"],[43,"Q4_K_L"],[44,"Q5_K_S"],[45,"Q5_K_M"],[46,"Q5_K_L"],[47,"Q6_K_S"]
   ]'
   FLAGS="--token-embedding-type Q6_K --output-tensor-type Q6_K --layer-types-high"

Comparison:

Quant	size	PPL	Comment
IQ4_XS	16.6e9	7.1	IQ4_XS with default embedding and output
Q4_K_H	16.9e9	7.1	Hybrid quant with Q6_K embedding Q6_K output

Usage:

Qwen3-VL-30B-A3B Instruct is a vision capable moe model. It can be used together with its multimedia projector layers to process images and text inputs and generate text outputs. The mmproj file is made available in this repository. To test vision mode follow the docs in the mtmd readme in the tools directory of the source tree https://github.com/ggml-org/llama.cpp/blob/master/tools/mtmd/README.md .

This moe model can be run efficiently by offloading expert layers to CPU. Some example configs for use with a 12G VRAM GPU:

# Offload all experts to CPU, maximize context size on GPU : 22tps gen rate on 9900k+4070
OT="-ot exps=CPU -ngl 99"

# Offload only layers 30 to 47 experts to CPU for max inference speed with usable context size : 33tps gen rate on 9900k+4070
OT="-ot blk\.3[0-9]|4[0-7].*exps=CPU -ngl 99"

# Offload layers 25 to 47 experts to CPU to give bigger context size with still high gen speed : 27tps gen rate on 9900k+4070
OT="-ot blk\.2[5-9]|3[0-9]|4[0-7].*exps=CPU -ngl 99"

Llama.cpp minimum version to run Qwen3-VL series should be 6915 with recommended 6936 and above.

Benchmarks:

A full set of vision benchmarks for the model will eventually be given here: https://huggingface.co/spaces/steampunque/benchlm

Download the file from below:

Link	Type	Size/e9 B	Notes
Qwen3-VL-30B-A3B-Instruct.Q4_K_H.gguf	Q4_K_H	16.9e9 B	~IQ4_XS size
Qwen3-VL-30B-A3B-Instruct.mmproj.gguf	F16	1.1e9 B	multimedia projector

A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

https://github.com/ggml-org/llama.cpp/discussions/13040

Downloads last month: 91

GGUF

Model size

31B params

Architecture

qwen3vlmoe

Hardware compatibility

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for steampunque/Qwen3-VL-30B-A3B-Instruct-MP-GGUF

Base model

Qwen/Qwen3-VL-30B-A3B-Instruct

Quantized

(58)

this model