Instructions to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF",
	filename="mmproj-qwen3.5-9b-nvfp4-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/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16

LM Studio
Jan

vLLM

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16

Ollama
How to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with Ollama:
```
ollama run hf.co/FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16
```

Unsloth Studio

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF to start chatting

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-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/Qwen3.5-9B-NVFP4-GGUF:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16
```

Lemonade

How to use FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.5-9B-NVFP4-GGUF-F16

List all available models

lemonade list

Qwen3.5-9B-NVFP4-GGUF

NVFP4 GGUF quantization of Qwen3.5-9B, Alibaba Cloud's efficient 9B multimodal foundation model with 262K context, 201 languages, and hybrid Gated DeltaNet + Gated Attention architecture.

Optimized for NVIDIA Blackwell GPUs with native FP4 tensor core acceleration.

About NVFP4

What is NVFP4?

NVFP4 is NVIDIA's native 4-bit floating-point quantization format introduced with the Blackwell architecture (SM120+). Unlike traditional integer quantization (Q4_0, Q4_K_M, etc.), NVFP4 stores weights in FP4 (E4M3) format — a 4-bit floating-point representation with 1 sign bit, 4 exponent bits, and 3 mantissa bits.

The key difference from INT4 formats:

Property	NVFP4 (FP4)	INT4 (Q4_X)
Representation	Floating-point	Integer
Dynamic range	~±240	~±7
Block size	16	32
Scale format	FP16 (E4M3)	FP16
Hardware support	Blackwell SM120+ (native tensor cores)	All GPUs (software)
Zero-shot perplexity	Near-identical to FP16	Slight degradation

Why use NVFP4?

Blackwell-native acceleration: NVFP4 is processed natively on Blackwell FP4 tensor cores, delivering up to 2x throughput vs INT4 software kernels on the same hardware.
Better dynamic range: Floating-point 4-bit preserves more information for outlier weights compared to integer quantization, resulting in lower perplexity degradation.
Memory efficiency: At ~4.74 bits per weight (BPW), a 9B model fits in ~5 GB — well within 16 GB VRAM with room for 262K context.
No dequantization overhead: Unlike INT4 formats that require runtime dequantization, FP4 operates directly on tensor cores for both compute and memory bandwidth.

When to use NVFP4 vs other formats

NVFP4: Best choice if you have a Blackwell GPU (RTX 5060 Ti, RTX 5090, B200, etc.)
Q4_K_M / Q4_0: Better for pre-Blackwell GPUs (Ampere, Ada Lovelace) or CPU inference
Q8_0 / F16: Use when maximum quality is needed and memory is not a constraint

Files

Filename	Type	Size	Description
`qwen3.5-9b-nvfp4.gguf`	NVFP4	5.31 GB	Quantized text model weights
`mmproj-qwen3.5-9b-nvfp4-f16.gguf`	F16 mmproj	918 MB	Vision encoder projector

Quantization Details

Property	Value
Format	NVIDIA NVFP4 (E4M3 FP4)
Block size	16
Effective BPW	4.74
Hardware target	Blackwell SM120+
VRAM required (text)	~5 GB
VRAM required (text + vision + 32K ctx)	~7 GB

Model Description

Qwen3.5-9B features:

Hybrid architecture: Alternating linear attention (Gated DeltaNet) and full attention layers for efficient long-context processing
262K context window: Native support for 262,144 token sequences
Vision capabilities: Built-in vision encoder with 27-layer ViT for image understanding
Multi-Token Prediction: MTP head enabling speculative decoding for faster generation
Multilingual: Strong performance across 201 languages

Usage

llama.cpp (CLI)

# Text + Image
llama-cli \
  -m qwen3.5-9b-nvfp4.gguf \
  --mmproj mmproj-qwen3.5-9b-nvfp4-f16.gguf \
  --image photo.jpg \
  -p "Describe this image in detail"

# Text only
llama-cli \
  -m qwen3.5-9b-nvfp4.gguf \
  -p "Explain quantum computing in simple terms" \
  -n 512

# OpenAI-compatible server
llama-server \
  -m qwen3.5-9b-nvfp4.gguf \
  --mmproj mmproj-qwen3.5-9b-nvfp4-f16.gguf \
  --port 8080

llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF",
    filename="qwen3.5-9b-nvfp4.gguf",
    n_gpu_layers=-1,
)

response = llm.create_chat_completion([
    {"role": "user", "content": "What is the capital of France?"}
])
print(response["choices"][0]["message"]["content"])

Direct download

from huggingface_hub import hf_hub_download

for filename in ["qwen3.5-9b-nvfp4.gguf", "mmproj-qwen3.5-9b-nvfp4-f16.gguf"]:
    hf_hub_download(
        repo_id="FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF",
        filename=filename,
        local_dir="./models"
    )

Quantization Pipeline

1. Download source weights
   huggingface_hub.snapshot_download("Qwen/Qwen3.5-9B")

2. Convert text model to F16 GGUF
   convert_hf_to_gguf.py --outtype f16

3. Extract vision encoder
   convert_hf_to_gguf.py --mmproj --outtype f16

4. Quantize to NVFP4
   llama-quantize qwen3.5-9b-f16.gguf qwen3.5-9b-nvfp4.gguf NVFP4

Quantization completed in ~5 minutes on the hardware below.

Hardware

Component	Specification
GPU	NVIDIA GeForce RTX 5060 Ti (Blackwell SM120)
VRAM	16 GB GDDR7
System RAM	64 GB DDR4

License

The original Qwen3.5-9B is released under Apache 2.0. These quantized weights inherit that license.

Downloads last month: 1,455

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(287)

this model

Collection including FreedomAISVR/Qwen3.5-9B-NVFP4-GGUF

QWEN NVFP4 GGUF

Collection

4 items • Updated 17 days ago • 1