Instructions to use Melvin56/Qwen3-4B-ik_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 Melvin56/Qwen3-4B-ik_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 Melvin56/Qwen3-4B-ik_GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Melvin56/Qwen3-4B-ik_GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Melvin56/Qwen3-4B-ik_GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Melvin56/Qwen3-4B-ik_GGUF:BF16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Melvin56/Qwen3-4B-ik_GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf Melvin56/Qwen3-4B-ik_GGUF:BF16

Use Docker

docker model run hf.co/Melvin56/Qwen3-4B-ik_GGUF:BF16

Llama new
LM Studio
Jan

vLLM

How to use Melvin56/Qwen3-4B-ik_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Melvin56/Qwen3-4B-ik_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": "Melvin56/Qwen3-4B-ik_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Melvin56/Qwen3-4B-ik_GGUF:BF16

Ollama
How to use Melvin56/Qwen3-4B-ik_GGUF with Ollama:
```
ollama run hf.co/Melvin56/Qwen3-4B-ik_GGUF:BF16
```
Unsloth Desktop

How to use Melvin56/Qwen3-4B-ik_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Melvin56/Qwen3-4B-ik_GGUF:BF16

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": "Melvin56/Qwen3-4B-ik_GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Melvin56/Qwen3-4B-ik_GGUF with Docker Model Runner:
```
docker model run hf.co/Melvin56/Qwen3-4B-ik_GGUF:BF16
```

Lemonade

How to use Melvin56/Qwen3-4B-ik_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Melvin56/Qwen3-4B-ik_GGUF:BF16

Run and chat with the model

lemonade run user.Qwen3-4B-ik_GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use Melvin56/Qwen3-4B-ik_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 Melvin56/Qwen3-4B-ik_GGUF:BF16

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 Melvin56/Qwen3-4B-ik_GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Melvin56/Qwen3-4B-ik_GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Melvin56/Qwen3-4B-ik_GGUF:BF16

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 "Melvin56/Qwen3-4B-ik_GGUF:BF16" \
  --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"

Melvin56/Qwen3-4B-ik_GGUF

Quant for ik_llama.cpp

Build: 3680 (a2d24c97)

Original Model : Qwen/Qwen3-4B

I used imatrix to create all these quants using this Dataset.

Perplexity measurement methodology.

I tested all quants using ik_llama.cpp build 3680 (a2d24c97)

ik_llama.cpp/build/bin/llama-perplexity \
-m .gguf \
--ctx-size 512 \
--ubatch-size 512 \
-f wikitext-2-raw/wiki.test.raw \
-fa \
-ngl 999

Raw data

Quant	Size (GB)	PPL
BF16	8.05	14.3308 +/- 0.13259
IQ6_K	3.34	14.2810 +/- 0.13159
IQ5_K	2.82	14.5004 +/- 0.13465
IQ4_K	2.38	14.5280 +/- 0.13414
IQ4_KS	2.22	15.2121 +/- 0.14294

	CPU (AVX2)	CPU (ARM NEON)	Metal	cuBLAS	rocBLAS	SYCL	CLBlast	Vulkan	Kompute
K-quants	✅	✅	✅	✅	✅	✅	✅ 🐢5	✅ 🐢5	❌
I-quants	✅ 🐢4	✅ 🐢4	✅ 🐢4	✅	✅	Partial¹	❌	❌	❌

✅: feature works
🚫: feature does not work
❓: unknown, please contribute if you can test it youself
🐢: feature is slow
¹: IQ3_S and IQ1_S, see #5886
²: Only with -ngl 0
³: Inference is 50% slower
⁴: Slower than K-quants of comparable size
⁵: Slower than cuBLAS/rocBLAS on similar cards
⁶: Only q8_0 and iq4_nl