Instructions to use novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "novelaide/Qwen3.5-4B-Q4_K_M-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": "novelaide/Qwen3.5-4B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

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": "novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-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 novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use novelaide/Qwen3.5-4B-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M

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 "novelaide/Qwen3.5-4B-Q4_K_M-GGUF:Q4_K_M" \
  --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 Q4_K_M GGUF

This repository contains the exact immutable local-model asset used by NovelAide.

Provenance

Base model: Qwen/Qwen3.5-4B
Asset source: lmstudio-community/Qwen3.5-4B-GGUF
Pinned source revision: f9f88ac3e234be915e23811a6d28ea287bdb927e
Runtime: llama-cpp
NovelAide asset ID: qwen3.5-4b-q4-k-m
NovelAide CDN prefix: qwen3.5-4b-gguf

The base model is Qwen/Qwen3.5-4B; NovelAide consumes the LM Studio community GGUF quantization lmstudio-community/Qwen3.5-4B-GGUF.

Files

The NovelAide local package includes an upstream README.md. Hugging Face reserves that path for this model card, so the original bytes are published as UPSTREAM_README.md; its size and SHA-256 below remain unchanged.

File	Size	SHA-256
`UPSTREAM_README.md`	0.00 MiB	`e1b3ca9c804ec81f9d0f8e51eab46d4e0e1b18521e7436bcb95736fb3d0414ae`
`Qwen3.5-4B-Q4_K_M.gguf`	2582.09 MiB	`25082a7dd3776cc3c741c6347d3bd04523f05796607b3fbc32fa3a25dfa1418c`

Usage

Use the GGUF files with a compatible llama.cpp runtime and the ONNX files with a compatible ONNX / Transformers.js runtime. NovelAide pins the exact files and checksums shown above; do not substitute similarly named quantizations.

License and attribution

The model asset follows the upstream apache-2.0 license. Review the linked base model and asset source model cards for their complete terms, limitations, and attribution requirements. NovelAide is not affiliated with or endorsed by the upstream model authors.

Downloads last month: 115

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for novelaide/Qwen3.5-4B-Q4_K_M-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(405)

this model