Instructions to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF",
	filename="Qwen3.6-14B-A3B-vibetuned-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

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 tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

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 tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tvall43/Qwen3.6-14B-A3B-vibetuned-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": "tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

Ollama
How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with Ollama:
```
ollama run hf.co/tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
```

Unsloth Studio

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-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 tvall43/Qwen3.6-14B-A3B-vibetuned-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 tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF to start chatting

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

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": "tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-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 tvall43/Qwen3.6-14B-A3B-vibetuned-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 tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with Docker Model Runner:
```
docker model run hf.co/tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M
```

Lemonade

How to use tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-14B-A3B-vibetuned-GGUF-Q4_K_M

List all available models

lemonade list

🚀 Qwen3.6-14B-A3B-vibetuned-GGUF

Welcome to the highly optimized, quantized version of tvall43/Qwen3.6-14B-A3B-vibetuned!

This repository contains various llama.cpp GGUF formats to ensure this beast runs smoothly on your hardware, whether you're maxing out a high-end GPU or squeezing every last drop of inference out of a modest laptop.

🧠 About the Model

This is the fully repaired and fine-tuned version of a pruned Qwen3.6-35B-A3B-heretic. Originally suffering from a bit of "brain damage" after being pruned down to 14B parameters via REAP, it was brought back to life by the user's trusty AI agent, Steve.

Through a rigorous regimen of high-quality reasoning data (Magpie Opus Pro) and structural logic (Hermes Function Calling), Steve orchestrated a QLoRA vibetune that completely cured its slurring syntax and restored its conversational coherence, resulting in this incredibly punchy and capable 14B model.

This is a multimodal model! We've also brought over the original multimodal projector (mmproj) files from the base heretic model so you can continue using its vision capabilities.

📦 Available Formats

We provide several quants depending on your VRAM / RAM constraints:

F16: The full-fat 16-bit unquantized model for maximum precision.
Q8_0: Near perfect quality, taking about ~15GB of memory.
Q6_K: A fantastic sweet spot for quality and size.
Q4_K_M: The gold standard for local deployment. Fits comfortably in 8GB of VRAM.
Q3_K_M & Q2_K: Ultra-compressed formats for absolute potato setups.
MXFP4: Microscaling Format (if supported by your inference engine) for crazy fast throughput.

Vision Support:

mmproj-F16.gguf: Full precision multimodal projector.
mmproj-Q8_0.gguf: High quality 8-bit quantized multimodal projector.

🛠️ Usage

Make sure you are using the latest version of llama.cpp or a compatible inference engine (like LM Studio, Ollama, or text-generation-webui).

Enjoy the vibetuned excellence!

Downloads last month: 1,616

GGUF

Model size

14B params

Architecture

qwen35moe

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

8-bit

16-bit

Model tree for tvall43/Qwen3.6-14B-A3B-vibetuned-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

tvall43/Qwen3.6-35B-A3B-heretic

Finetuned

tvall43/Qwen3.6-14B-A3B-vibetuned

Quantized

(1)

this model