Instructions to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF",
	filename="mmproj-qwen35-4b-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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

LM Studio
Jan

vLLM

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-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": "FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

Ollama
How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with Ollama:
```
ollama run hf.co/FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
```

Unsloth Studio

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF to start chatting

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

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": "FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

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 FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16
```

Lemonade

How to use FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.5-4B-Instruct-MXFP4-GGUF-F16

List all available models

lemonade list

Qwen3.5-4B-Instruct-MXFP4-GGUF

MXFP4 (OCP Microscaling FP4) GGUF quantization of the Qwen3.5-4B-Instruct multimodal language model with thinking disabled by default.

About MXFP4

MXFP4 (E2M1) is the open-standard 4-bit floating-point format defined by the OCP Microscaling Formats (MX) specification. Unlike block-scaled integer formats (Q4_K_M), MXFP4 uses per-group scaling factors (block size 32) with shared exponent via the E2M1 format (2 exponent bits, 1 mantissa bit). This provides better dynamic range utilization than integer formats and works across GPU vendors (NVIDIA, AMD, Intel) and CPUs.

Key Advantages

Cross-vendor: Runs on any GPU or CPU (no vendor lock-in)
E2M1 format: 2 exponent bits + 1 mantissa bit + shared scale per 32 elements
Floating-point: Better dynamic range than integer quantization
Open standard: OCP MX specification, widely supported

Repo Contents

Filename	Type	Size	Description
`qwen35-4b-instruct-mxfp4.gguf`	Text model	2.58 GB	MXFP4 quantized model (no MTP head)
`mmproj-qwen35-4b-f16.gguf`	Vision encoder	676 MB	SigLIP vision projector (F16)

Quantization Details

Property	Value
Format	MXFP4 (OCP E2M1)
Block size	32 elements
BPW	~4.90
Architecture	qwen35 (no MTP, 426 tensors)
Target hardware	Universal (CPU, AMD, NVIDIA, Intel)
Thinking	Disabled by default (opt-in via `enable_thinking=true`)
MTP	Disabled (`--no-mtp`)

Usage

llama.cpp

# Basic text generation (thinking disabled by default)
./llama-cli -m qwen35-4b-instruct-mxfp4.gguf -p "What is the capital of France?" -n 256

# Vision (requires mmproj)
./llama-cli -m qwen35-4b-instruct-mxfp4.gguf --mmproj mmproj-qwen35-4b-f16.gguf -p "Describe this image" --image photo.jpg -n 256

# Enable thinking
./llama-cli -m qwen35-4b-instruct-mxfp4.gguf -p "Solve: 2+2=?" -n 512 -e enable_thinking=true

Python

from llama_cpp import Llama

llm = Llama(
    model_path="qwen35-4b-instruct-mxfp4.gguf",
    n_ctx=8192,
    chat_format="qwen3",
)

# Basic chat (no thinking)
output = llm.create_chat_completion([{"role": "user", "content": "What is AI?"}])

# With thinking enabled
output = llm.create_chat_completion(
    [{"role": "user", "content": "Solve 2+2=?"}],
    extra_body={"enable_thinking": True},
)

Download

huggingface-cli download FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF --local-dir . --local-dir-use-symlinks False

Original Model

Qwen3.5-4B is Alibaba Cloud's efficient multimodal foundation model (Apache 2.0, March 2026) featuring:

Hybrid Gated DeltaNet + Gated Attention (3:1 ratio)
262K native context (extensible to 1M)
Text + Image + Video input
201 language support

Conversion

python convert_hf_to_gguf.py --no-mtp --outfile qwen35-4b-f16.gguf D:\qwen35-4b-src
python convert_hf_to_gguf.py --mmproj --outfile mmproj-qwen35-4b-f16.gguf D:\qwen35-4b-src
llama-quantize.exe qwen35-4b-f16.gguf qwen35-4b-instruct-mxfp4.gguf MXFP4

License

Apache 2.0 (same as Qwen3.5-4B)

Downloads last month: 399

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for FreedomAISVR/Qwen3.5-4B-Instruct-MXFP4-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(227)

this model