Instructions to use YoozLabs/Qwen3.5-4B-qat-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 YoozLabs/Qwen3.5-4B-qat-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 YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

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 YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

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 YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

Use Docker

docker model run hf.co/YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use YoozLabs/Qwen3.5-4B-qat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YoozLabs/Qwen3.5-4B-qat-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": "YoozLabs/Qwen3.5-4B-qat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

Ollama
How to use YoozLabs/Qwen3.5-4B-qat-GGUF with Ollama:
```
ollama run hf.co/YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
```
Unsloth Desktop

How to use YoozLabs/Qwen3.5-4B-qat-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

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": "YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use YoozLabs/Qwen3.5-4B-qat-GGUF with Docker Model Runner:
```
docker model run hf.co/YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0
```

Lemonade

How to use YoozLabs/Qwen3.5-4B-qat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.5-4B-qat-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use YoozLabs/Qwen3.5-4B-qat-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 YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

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 YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use YoozLabs/Qwen3.5-4B-qat-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0

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 "YoozLabs/Qwen3.5-4B-qat-GGUF:Q4_0" \
  --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"

Qwen3.5-4B (Yooz QAT, GGUF Q4_0)

What this is

The GGUF (Q4_0) release of Yooz Labs' quantization-aware-trained (QAT) Qwen3.5-4B -- the same weights as Qwen3.5-4B-qat-lean-4bit-mlx, converted for llama.cpp. Stock 4-bit PTQ builds of this model break its aggregation abilities outright (variable-tracking collapses to 0.00 on the MLX product grid); this build is trained to tolerate 4-bit quantization via knowledge distillation from the full-precision bf16 model, so the quantized weights reproduce the original model's behavior -- aggregation AND multi-turn recall -- at both short and long context.

Provenance

Base checkpoint: Qwen/Qwen3.5-4B
QAT training: Yooz Labs, 2026-07 -- knowledge distillation from the bf16 base model under fake-quantization matching the MLX 4-bit group-64 grid (the training target; this GGUF is the same trained weights re-quantized to Q4_0 for llama.cpp). Full-parameter training at this size. Training recipes are not published.
Conversion: llama.cpp convert_hf_to_gguf.py + llama-quantize to Q4_0 (build e3546c7). The converter's block count is set to 32 layers, matching this model's actual depth.
Harness: benchmarks/ (infinite repo, Yooz Labs).

Validation

The comprehensive A/B (needle-in-a-haystack, RULER-style aggregation, MRCR) was run on the MLX build of these exact weights, since that is where the full n=30, two-context-length harness lives; see Qwen3.5-4B-qat-lean-4bit-mlx for the full table and chart. Summary:

Task	Context	4-bit PTQ, same grid	Yooz QAT 4-bit
NIAH single	8K	1.00	1.00
NIAH multikey	8K	1.00	0.97
Variable tracking	8K	0.00	0.97
Frequent words	8K	0.12	0.83
MRCR 2-needle	8K	0.97	0.97
NIAH single	32K	0.97	1.00
NIAH multikey	32K	1.00	0.97
Variable tracking	32K	0.89	0.99
Frequent words	32K	0.22	0.77
MRCR 2-needle	32K	0.96	0.96

This GGUF file was separately spot-checked through the actual llama.cpp Q4_0 path (not just the MLX grid) at 8K context, n=30, on an A100-SXM4-80GB (AMD EPYC 7713, Ubuntu 22.04, llama.cpp build e3546c7):

Task	Context	Yooz QAT 4-bit (this GGUF file)
Variable tracking	8K	0.96
Frequent words	8K	0.62
MRCR 2-needle	8K	0.94

Consistent with the MLX numbers above -- the fix survives re-quantization to a different format.

Usage

llama-cli -m Qwen3.5-4B-qat-Q4_0.gguf -p "List the first five prime numbers." -n 64

Or with llama-server for an OpenAI-compatible endpoint:

llama-server -m Qwen3.5-4B-qat-Q4_0.gguf --port 8080

An MLX build of the same QAT weights is available at YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx.

About Yooz Labs

Maintained by Yooz Labs -- sovereign, on-device AI for macOS. Everything we ship runs locally; nothing goes to a cloud. This build comes out of our long-context research line, where we found and quantified the PTQ aggregation crater -- and then trained it away.

Questions, issues, or corrections: dev@yooz.info

License and attribution

Apache 2.0, inherited from the base checkpoint Qwen/Qwen3.5-4B. Qwen is a model family by Alibaba Cloud; this is an independent, unofficial QAT build, not distributed, endorsed, or certified by Alibaba.