Instructions to use Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Abiray/ComfyUI-Qwen3-VL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abiray/ComfyUI-Qwen3-VL-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": "Abiray/ComfyUI-Qwen3-VL-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/Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M

Ollama
How to use Abiray/ComfyUI-Qwen3-VL-GGUF with Ollama:
```
ollama run hf.co/Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Abiray/ComfyUI-Qwen3-VL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/ComfyUI-Qwen3-VL-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": "Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Abiray/ComfyUI-Qwen3-VL-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/ComfyUI-Qwen3-VL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ComfyUI-Qwen3-VL-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-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 Abiray/ComfyUI-Qwen3-VL-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Abiray/ComfyUI-Qwen3-VL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/ComfyUI-Qwen3-VL-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 "Abiray/ComfyUI-Qwen3-VL-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"

ComfyUI Qwen3-VL GGUF (8B & 4B) — Unified Hybrid & Split `mmproj` Editions

GGUF quantizations of Qwen3-VL extracted from Comfy-Org's Qwen3-VL repackaged weights.

This repository provides two distinct formats depending on your runtime:

🔥 NEW: Unified Single-File Hybrid GGUFs (*_vision_q8_0.gguf) — Combines the K-quantized LLM backbone (Q4_K_M / Q5_K_M) and the Q8_0 Vision Tower + DeepStack Mergers + 5D Conv3d shape metadata (comfy.gguf.orig_shape) inside a single file.
Split LLM + Standalone mmproj GGUFs — Standard two-file format for llama.cpp, llama-server, Ollama, and split VLM loaders.

Model Overview

Original Weights Source: Comfy-Org/Qwen3-VL
Underlying Architecture: Alibaba Cloud Qwen3-VL (Qwen3VLForConditionalGeneration / qwen3vl)
Hybrid Format Vision Precision: Q8_0 Vision Tower & DeepStack Mergers + F32 LayerNorms/Biases + preserved 5D [1152, 3, 2, 16, 16] patch embedding metadata
Split Format Projector Precision: Standalone F16 GGUF (mmproj) preserving full vision patch fidelity
Quantization Engine: llama.cpp k-quants + custom ComfyUI-GGUF-Loader hybrid tensor packer

Available Files & Specifications

1. Unified Single-File Hybrid Series (Recommended for ComfyUI)

Contains both the Language Backbone (blk.*) and Vision Tower (model.visual.*) in a single GGUF file.

File Name	LLM Precision	Vision Precision	File Size	Description
`qwen3vl_8b_q4_k_m_vision_q8_0.gguf`	Q4_K_M	Q8_0 / F32	5.62 GB	All-in-one hybrid GGUF. Best speed/VRAM balance for `ComfyUI-GGUF-Loader` (no external `mmproj` needed).
`qwen3vl_8b_q5_k_m_vision_q8_0.gguf`	Q5_K_M	Q8_0 / F32	~6.39 GB	All-in-one hybrid GGUF. Higher-precision text backbone paired with `Q8_0` vision & DeepStack mergers.

2. Split 8B Series (LLM + Standalone `mmproj`)

For llama.cpp, llama-server, or split-loader workflows.

File Name	Precision	File Size	Description
`mmproj-qwen3vl-8b-f16.gguf`	F16	1.08 GB	Standalone multimodal vision projector (pair with split 8B files below)
`qwen3vl-8b-Q4_K_M.gguf`	Q4_K_M	4.68 GB	Optimal balance of generation speed, memory, and accuracy
`qwen3vl-8b-Q5_K_M.gguf`	Q5_K_M	5.45 GB	Balanced higher-precision text backbone
`qwen3vl-8b-Q6_K.gguf`	Q6_K	6.26 GB	Near-lossless language reasoning and instruction following

3. Split 4B Series (LLM + Standalone `mmproj`)

File Name	Precision	File Size	Description
`mmproj-qwen3vl-4b-f16.gguf`	F16	0.78 GB	Standalone 4B Multimodal vision projector
`qwen3vl-4b-Q4_K_M.gguf`	Q4_K_M	2.33 GB	Ultra-lightweight edge quant for low-memory environments
`qwen3vl-4b-Q5_K_M.gguf`	Q5_K_M	2.69 GB	Higher-precision 4B variant

Quickstart & Usage

Option A: Unified Single-File Setup

Download either qwen3vl_8b_q4_k_m_vision_q8_0.gguf or qwen3vl_8b_q5_k_m_vision_q8_0.gguf and place it into:
```
ComfyUI/models/text_encoders/
# or
ComfyUI/models/clip/
```
Load it directly inside ComfyUI using the CLIPLoader (GGUF) node

Option B: Split Two-File Setup (`llama.cpp` / Split ComfyUI Loaders)

Place your desired language GGUF (e.g., qwen3vl-8b-Q4_K_M.gguf) into:
```
ComfyUI/models/unet/
# or
ComfyUI/models/text_encoders/
```
Place the matching projector (e.g., mmproj-qwen3vl-8b-f16.gguf) into:
```
ComfyUI/models/clip_vision/
```

Load the model using your split GGUF loader or via llama.cpp CLI/Server:

llama-server -m qwen3vl-8b-Q4_K_M.gguf --mmproj mmproj-qwen3vl-8b-f16.gguf

Technical Verification (Hybrid Series)

Both qwen3vl_8b_q4_k_m_vision_q8_0.gguf and qwen3vl_8b_q5_k_m_vision_q8_0.gguf have been validated end-to-end:

750 Total Tensors: 399 LLM tensors (Q4_K_M or Q5_K_M) + 351 Vision tensors (Q8_0 weights + F32 norms/biases).
5D Patch Embedding Metadata: Includes comfy.gguf.orig_shape.model.visual.patch_embed.proj.weight = [1152, 3, 2, 16, 16] for 3D temporal-spatial patch projection.
DeepStack Mergers: All 3 DeepStack spatial mergers ([4096, 4608]) and final vision-to-LLM merger verified with zero NaN/Inf values during multimodal forward passes.

Acknowledgements

Alibaba Cloud Qwen Team for the foundational Qwen3-VL models.
Comfy-Org for packaging the unified BF16 safetensors weights.
Georgi Gerganov and the GGML/llama.cpp contributors for GGUF architecture and quantization tooling.

Downloads last month: 4,235

GGUF

Model size

9B params

Architecture

qwen3vl

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for Abiray/ComfyUI-Qwen3-VL-GGUF

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

Comfy-Org/Qwen3-VL

Quantized

(1)

this model

ComfyUI Qwen3-VL GGUF (8B & 4B) — Unified Hybrid & Split mmproj Editions

Model Overview

Available Files & Specifications

1. Unified Single-File Hybrid Series (Recommended for ComfyUI)

2. Split 8B Series (LLM + Standalone mmproj)

3. Split 4B Series (LLM + Standalone mmproj)

Quickstart & Usage

Option A: Unified Single-File Setup

Option B: Split Two-File Setup (llama.cpp / Split ComfyUI Loaders)

Technical Verification (Hybrid Series)

Acknowledgements

Model tree for Abiray/ComfyUI-Qwen3-VL-GGUF

ComfyUI Qwen3-VL GGUF (8B & 4B) — Unified Hybrid & Split `mmproj` Editions

2. Split 8B Series (LLM + Standalone `mmproj`)

3. Split 4B Series (LLM + Standalone `mmproj`)

Option B: Split Two-File Setup (`llama.cpp` / Split ComfyUI Loaders)