Instructions to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NobodyWho/Qwen_Qwen3.5-4B-GGUF",
	filename="Qwen_Qwen3.5-4B-BF16-vendor-sampling.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

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 NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

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 NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NobodyWho/Qwen_Qwen3.5-4B-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": "NobodyWho/Qwen_Qwen3.5-4B-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/NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

Ollama
How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with Ollama:
```
ollama run hf.co/NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
```

Unsloth Studio

How to use NobodyWho/Qwen_Qwen3.5-4B-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 NobodyWho/Qwen_Qwen3.5-4B-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 NobodyWho/Qwen_Qwen3.5-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NobodyWho/Qwen_Qwen3.5-4B-GGUF to start chatting

How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

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": "NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NobodyWho/Qwen_Qwen3.5-4B-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 NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

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 NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M
```

Lemonade

How to use NobodyWho/Qwen_Qwen3.5-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NobodyWho/Qwen_Qwen3.5-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen_Qwen3.5-4B-GGUF-Q4_K_M

List all available models

lemonade list

NobodyWho/Qwen_Qwen3.5-4B-GGUF

Overview

GGUF quantization of Qwen3.5-4B, prepared for NobodyWho: it works with NobodyWho out of the box, with Qwen's recommended sampling metadata embedded in every quant, and is verified with NobodyWho's test suite. Qwen3.5 is Alibaba's latest small-model family — natively multimodal (text + image), with strong reasoning and best-in-class tool calling for its size.

Model Capabilities

Text generation — instruction-following chat
Tool calling — native function calling with grammar-constrained output (14/14 on NobodyWho's suite)
Vision — image understanding via the companion mmproj-BF16.gguf projection model
Reasoning — thinking mode (on by default)
Long context — up to 256k tokens
Multilingual — broad language coverage

Available Quantizations

File	Approach	Tool-calling tests
`Qwen_Qwen3.5-4B-BF16-vendor-sampling.gguf`	Vendor sampling injected	14/14
`Qwen_Qwen3.5-4B-Q8_0-vendor-sampling.gguf`	Vendor sampling injected	14/14
`Qwen_Qwen3.5-4B-Q4_K_M-vendor-sampling.gguf`	Vendor sampling injected	14/14
`mmproj-BF16.gguf`	Vision projection (use with any of the above)	—

Verified with NobodyWho's tool-calling suite across BF16 / Q8_0 / Q4_K_M (14/14 each, June 2026); vision, reasoning, and multilingual verified. The upstream GGUF has no general.sampling.* metadata, so the -vendor-sampling files embed Qwen's recommended sampler (see INJECTION.md).

Quick Start

Using the NobodyWho library:

from nobodywho import Chat

chat = Chat("huggingface:NobodyWho/Qwen_Qwen3.5-4B-GGUF/Qwen_Qwen3.5-4B-Q4_K_M-vendor-sampling.gguf")
response = chat.ask("What is the capital of Denmark?").completed()
print(response)  # The capital of Denmark is Copenhagen.

Vision

from nobodywho import Model, Chat, Prompt, Image, Text

model = Model(
    "huggingface:NobodyWho/Qwen_Qwen3.5-4B-GGUF/Qwen_Qwen3.5-4B-Q4_K_M-vendor-sampling.gguf",
    projection_model_path="huggingface:NobodyWho/Qwen_Qwen3.5-4B-GGUF/mmproj-BF16.gguf",
)
chat = Chat(model=model, system_prompt="You are a helpful assistant.")
response = chat.ask(Prompt([
    Text("What is in this image?"),
    Image("./photo.png"),
])).completed()
print(response)

llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="NobodyWho/Qwen_Qwen3.5-4B-GGUF",
    filename="Qwen_Qwen3.5-4B-Q4_K_M-vendor-sampling.gguf",
)

Model Specifications

Parameters: 4B
Context length: 262,144 tokens (256K)
License: Apache 2.0
Base model: Qwen/Qwen3.5-4B
Architecture: qwen35 (vision-capable)

Licensing / Credits

Licensed under Apache 2.0 (unchanged from upstream). All model credit belongs to the Qwen team, Alibaba Group. GGUF quantizations provided by unsloth.