Instructions to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF",
	filename="Qwen3-VL-8B-Thinking-Unredacted-MAX.BF16.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"image\": \"cat.png\",\n    \"prompt\": \"Turn the cat into a tiger.\"\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

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 prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

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 prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

Use Docker

docker model run hf.co/prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

LM Studio
Jan
Ollama
How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
```

Unsloth Studio new

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-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 prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-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 prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF to start chatting

Pi new

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

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": "prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

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 prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

Run Hermes

hermes

Docker Model Runner
How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16
```

Lemonade

How to use prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF:BF16

Run and chat with the model

lemonade run user.Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF-BF16

List all available models

lemonade list

Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF

Qwen3-VL-8B-Thinking-Unredacted-MAX is a highly advanced and unredacted evolution of the original Qwen3-VL-8B-Thinking model, meticulously fine-tuned through sophisticated abliterated training strategies that are specifically designed to minimize or neutralize internal refusal mechanisms while preserving and amplifying the model’s core multimodal reasoning capabilities, enabling it to understand and analyze complex visual inputs with exceptional depth and generate unrestricted, richly detailed, and contextually nuanced captions, explanations, and analyses across a wide spectrum of content, including artistic, technical, scientific, forensic, and abstract domains; as an 8-billion-parameter vision-language system, it delivers high-fidelity outputs with superior reasoning and descriptive accuracy compared to smaller variants, making it particularly suitable for advanced data annotation, accessibility enhancement, creative storytelling, historical or medical dataset curation, and rigorous red-teaming or bias evaluation studies, all while maintaining a careful balance between computational efficiency, output fidelity, and versatility, positioning it as a state-of-the-art tool for researchers, developers, and professionals who require unrestricted, high-precision vision-language reasoning and generation capabilities.

Qwen3-VL-8B-Thinking-Unredacted-MAX [GGUF]

File Name	Quant Type	File Size	File Link
Qwen3-VL-8B-Thinking-Unredacted-MAX.BF16.gguf	BF16	16.4 GB	Download
Qwen3-VL-8B-Thinking-Unredacted-MAX.Q8_0.gguf	Q8_0	8.71 GB	Download
Qwen3-VL-8B-Thinking-Unredacted-MAX.mmproj-bf16.gguf	mmproj-bf16	1.16 GB	Download
Qwen3-VL-8B-Thinking-Unredacted-MAX.mmproj-q8_0.gguf	mmproj-q8_0	752 MB	Download