Instructions to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

Use Docker

docker model run hf.co/catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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": "catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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/catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

Ollama
How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with Ollama:
```
ollama run hf.co/catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
```

Unsloth Studio

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF to start chatting

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

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": "catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with Docker Model Runner:
```
docker model run hf.co/catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4
```

Lemonade

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-NVFP4-Fast-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

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 catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4

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 "catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF:NVFP4" \
  --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"

Qwen 3.6 35B A3B NVFP4 Fast GGUF

About

This model is an unmodified GGUF quantization of unsloth/Qwen3.6-35B-A3B-NVFP4-Fast, made with the llama.cpp conversion tool. Please refer to unsloth repository for quality metrics. Your feedback, contributions, optimization proposals and questions are highly appreciated.

This GGUF is primarily intended to be run fully on the GPU without offloading to the CPU. However, you can absolutely run it with offloading. The relevant guides are provided in this repo.

Speed metrics

I've tested this model on my setup (5070 Ti 16GB, 5060 Ti 16GB, 32GB DDR5). Token generation and prefill speeds will vary depending on your hardware. Please use the metrics below as a rough estimate of your potential performance.

Setup	Token generation, t/s	Prompt prefill, t/s
5070ti + 5060ti	~134.4	~3462
5070ti + CPU	~68.7	~324
5060ti + CPU	~51.0	~161

Quick start

This GGUF requires a recent build of llama.cpp. If the commands below raise a compatibility error, please update your llama.cpp version. All commands have been tested on llama.cpp version b9957 - ensure your version is >=b9957.

Agentic tasks

docker run --rm \
  --runtime nvidia \
  --gpus 2 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e HF_HUB_CACHE=/root/.cache/huggingface/hub \
  -p 8080:8080 \
  ghcr.io/ggml-org/llama.cpp:server-cuda13 \
  -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF \
  -np 1 \
  -ngl -1 \
  -c 256000 \
  --no-op-offload \
  --spec-type draft-mtp \
  --spec-draft-n-max 3

Speed-efficient

The token generation speeds listed below were achieved using varying prompt lengths, KV cache quantization, and the more powerful GPU 0. These optimizations simply let more computations to be done on 5070ti.

docker run --rm \
  --runtime nvidia \
  --gpus 2 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e HF_HUB_CACHE=/root/.cache/huggingface/hub \
  -p 8080:8080 \
  ghcr.io/ggml-org/llama.cpp:server-cuda13 \
  -hf catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF \
  -np 1 \
  -ngl -1 \
  -c 16000 \
  -ctk q8_0 \
  -ctv q8_0 \
  --tensor-split 2,1 \  # only for unequal gpus
  --no-op-offload \
  --spec-type draft-mtp \
  --spec-draft-n-max 3

Downloads last month: 1,098

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for catlilface/Qwen3.6-35B-A3B-NVFP4-Fast-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

unsloth/Qwen3.6-35B-A3B-NVFP4-Fast

Quantized

(3)

this model