Instructions to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers 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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
llama cli -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
llama cli -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
./llama-cli -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Use Docker

docker model run hf.co/meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

LM Studio
Jan

vLLM

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Ollama
How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with Ollama:
```
ollama run hf.co/meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
```

Unsloth Studio

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers 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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers 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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers to start chatting

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

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": "meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

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 "meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers" \
  --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 meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with Docker Model Runner:
```
docker model run hf.co/meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers
```

Lemonade

How to use meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Run and chat with the model

lemonade run user.Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3-VL-32B-Thinking-UD-Q4_K_XL

Distributed GGUF inference package for Mesh LLM

GGUF layer package for running Qwen3-VL-32B-Thinking-UD-Q4_K_XL across a local Mesh LLM cluster.

This package is derived from unsloth/Qwen3-VL-32B-Thinking-GGUF and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

Highlights

Run locally	Pool multiple machines	OpenAI-compatible	Package variant
Private inference on your hardware	Split layers across peers	Serve `/v1/chat/completions` locally	`UD-Q4_K_XL` layer package

Model Overview

Property	Value
Source model	unsloth/Qwen3-VL-32B-Thinking-GGUF
Model id	`unsloth/Qwen3-VL-32B-Thinking-GGUF:UD-Q4_K_XL`
Family	Qwen3
Parameter scale	32B
Quantization	`UD-Q4_K_XL`
Layer count	64
Activation width	5120
Package size	19.0 GB
Source file	`Qwen3-VL-32B-Thinking-UD-Q4_K_XL.gguf`
Package repo	meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Recommended Use

Local and private inference with Mesh LLM.
Multi-machine serving when the full GGUF is too large for one host.
OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: unsloth/Qwen3-VL-32B-Thinking-GGUF.

Quickstart

# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers" --split

# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models

# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "unsloth/Qwen3-VL-32B-Thinking-GGUF:UD-Q4_K_XL",
    "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
    "max_tokens": 128
  }'

Package Variant

Property	Value
Format	`layer-package`
Canonical source ref	`unsloth/Qwen3-VL-32B-Thinking-GGUF@main/Qwen3-VL-32B-Thinking-UD-Q4_K_XL.gguf`
Source revision	`main`
Source SHA-256	`37dda537201a9bcf06c085723e6743638660497aaefe4530adce080bc4ff6f92`
Skippy ABI	`0.1.25`
Package manifest SHA-256	`8d4c69517656b1988b8a5f28e3f5e2563c7408d3aaddf22f2704bbc2a38359d6`

What Is Included

Artifact	Path	Contents	SHA-256
Manifest	`model-package.json`	Package schema, source identity, checksums	`8d4c69517656b1988b8a5f28e3f5e2563c7408d3aaddf22f2704bbc2a38359d6`
Metadata	`shared/metadata.gguf`	0 tensors, 5.7 MB	`12dd0ed3a69c26792533a2d471b1a53f34874716e7cfd825f71b5f8533b2e89b`
Embeddings	`shared/embeddings.gguf`	1 tensors, 423.0 MB	`be9f33aeafa2a662331c25f468f21727ca0f4af56765e6acc54a14bdcaa4b5a5`
Output head	`shared/output.gguf`	2 tensors, 614.2 MB	`8a2836ef8a6ff2e7575bf611572a4c9c5e7ed43d4a0e808ce18e504bfe7322fe`
Transformer layers	`layers/layer-*.gguf`	64 layer artifacts, 704 tensors, 18.0 GB	`see model-package.json`

Validation

Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref main. Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

skippy-model-package write-package "/source/Qwen3-VL-32B-Thinking-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers-193/package"

Model tree for meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Base model

Qwen/Qwen3-VL-32B-Thinking

Quantized

unsloth/Qwen3-VL-32B-Thinking-GGUF

Quantized

(1)

this model

meshllm
/

Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers

Qwen3-VL-32B-Thinking-UD-Q4_K_XL

Highlights

Model Overview

Recommended Use

Quickstart

Package Variant

What Is Included

Validation

Links

Model tree for meshllm/Qwen3-VL-32B-Thinking-UD-Q4_K_XL-layers