Instructions to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ",
	filename="Qwen3.5-4B-Q2_K_XL.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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ 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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
# Run inference directly in the terminal:
./llama-cli -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

Use Docker

docker model run hf.co/ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

LM Studio
Jan

vLLM

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

Ollama
How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with Ollama:
```
ollama run hf.co/ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
```

Unsloth Studio

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ 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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ 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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ to start chatting

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

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": "ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

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 ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

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 "ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL" \
  --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"

Docker Model Runner
How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL
```

Lemonade

How to use ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ:Q2_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-4B-GGUF-GSQ-Q2_K_XL

List all available models

lemonade list

Qwen3.5-4B — GGUF Q2_K_XL refined with GSQ

GGUF Q2_K_XL checkpoint of Qwen/Qwen3.5-4B in which the discrete grid assignments have been refined with GSQ (Gumbel-Softmax Quantization), starting from the public Unsloth GGUF initialization and projected back into the same K-Quant format.

The optimized file runs unchanged on llama.cpp / Ollama and is a drop-in replacement for the corresponding standard GGUF checkpoint.

Paper: GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling (arXiv:2604.18556)
Paper page on HF: https://huggingface.co/papers/2604.18556
Code: https://github.com/IST-DASLab/GSQ
Collection: https://huggingface.co/collections/ISTA-DASLab/gsq

Quantization details

Base model: Qwen/Qwen3.5-4B
Starting point: Unsloth GGUF UD-Q2_K_XL
Released quantization: Q2_K_XL
Format: GGUF K-Quant
Pipeline: Unsloth GGUF init → GSQ Gumbel-Softmax refinement → re-pack into the same format
Runtime: llama.cpp, ollama, LM Studio, anything that consumes GGUF

Storage layout

This file is bit-for-bit standard GGUF Q2_K. GSQ only changes the values of the quantized weights by relearning the discrete grid assignments inside each K-Quant block.

As a result:

The file size matches the corresponding upstream Q2_K_XL file for the same model.
Any llama.cpp / ollama build that loads a regular Qwen3.5-4B Q2_K_XL GGUF should load this file with zero changes.
The Hugging Face UI reports the GGUF block type, e.g. Q2_K_XL, rather than per-tensor dtypes. This refers to the on-disk K-Quant encoding, not the precision of any optimizer state used during GSQ refinement.

Evaluation

We compare the GSQ-refined checkpoint against the Unsloth UD-Q2_K_XL checkpoint used as initialization.

Model	AIME 25	GPQA Diamond	IFEval	GSM8K	MMLU-Pro
Unsloth `UD-Q2_K_XL`	26.67	56.06	76.14	79.61	66.78
GSQ-refined `Q2_K_XL`	60.00	67.17	82.97	88.48	70.87

Evaluation notes

All evaluations are zeroshot. The Unsloth UD-Q2_K_XL model was evaluated with thinking disabled on all tasks, because its thinking mode was found to be broken and produced worse results.

For the GSQ-refined model:

AIME 25 and GPQA Diamond were evaluated with thinking enabled.
IFEval, GSM8K, and MMLU-Pro were evaluated with thinking disabled.

Token Efficiency

For MMLU-Pro, both models were evaluated with a maximum output budget of 32K tokens.

The Unsloth model consumed 55.32M output tokens in total.
The GSQ-refined model consumed 41.82M output tokens in total.

Usage with llama.cpp

hf download ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ \
  Qwen3.5-4B-Q2_K_XL.gguf --local-dir .

./llama-cli -m Qwen3.5-4B-Q2_K_XL.gguf -p "Hello"

Downloads last month: 110

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

2-bit

Model tree for ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(290)

this model

Collection including ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ

GSQ

Collection

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 9 items • Updated May 25 • 9

Paper for ISTA-DASLab/Qwen3.5-4B-GGUF-GSQ

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 9