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

Use Docker

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

LM Studio
Jan

vLLM

How to use tvall43/Qwen3.6-14B-A3B-VibeForged-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-VibeForged-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-VibeForged-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

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

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

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tvall43/Qwen3.6-14B-A3B-VibeForged-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tvall43/Qwen3.6-14B-A3B-VibeForged-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 "tvall43/Qwen3.6-14B-A3B-VibeForged-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"

🚀 Qwen3.6-14B-A3B-VibeForged-GGUF

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

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 an intensive vibetuning pass on thousands of real-world "vibecoding" sessions extracted from the user's OpenCode SQLite database, Steve orchestrated a QLoRA fine-tune that enforces strict <think>...</think> XML reasoning boundaries and clean JSON tool-calling syntax, resulting in this incredibly punchy and capable 14B MoE reasoning 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_MOE: Microscaling Format specifically targeted for this MoE model (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 VibeForged excellence!

Downloads last month: 392

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-VibeForged-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

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

Finetuned

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

Quantized

(1)

this model