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

Libraries

How to use wesjos/Qwen3-4B-toolcall-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("wesjos/Qwen3-4B-toolcall-GGUF", dtype="auto")

llama-cpp-python

How to use wesjos/Qwen3-4B-toolcall-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wesjos/Qwen3-4B-toolcall-GGUF",
	filename="Qwen3-4B-toolcall.F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M

Use Docker

docker model run hf.co/wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use wesjos/Qwen3-4B-toolcall-GGUF with Ollama:
```
ollama run hf.co/wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M
```

Unsloth Studio

How to use wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use wesjos/Qwen3-4B-toolcall-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesjos/Qwen3-4B-toolcall-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": "wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-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 wesjos/Qwen3-4B-toolcall-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use wesjos/Qwen3-4B-toolcall-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wesjos/Qwen3-4B-toolcall-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 "wesjos/Qwen3-4B-toolcall-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"

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

Lemonade

How to use wesjos/Qwen3-4B-toolcall-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Eval

+-------------+------------+-----------------+---------------+-------+---------+---------+
| Model       | Dataset    | Metric          | Subset        |   Num |   Score | Cat.0   |
+=============+============+=================+===============+=======+=========+=========+
| model       | gpqa       | AveragePass@1   | gpqa_extended |    50 |  0.34   | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | gpqa       | AveragePass@1   | gpqa_main     |    50 |  0.32   | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | gpqa       | AveragePass@1   | gpqa_diamond  |    50 |  0.32   | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | gpqa       | AveragePass@1   | OVERALL       |   150 |  0.3267 | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | gsm8k      | AverageAccuracy | main          |    50 |  0.76   | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Act.EM          | in_domain     |    42 |  0.2619 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Act.EM          | out_of_domain |    47 |  0.3617 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Act.EM          | OVERALL       |    89 |  0.3146 | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Plan.EM         | in_domain     |     0 |  0      | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Plan.EM         | out_of_domain |     0 |  0      | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Plan.EM         | OVERALL       |     0 |  0      | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | F1              | in_domain     |    42 |  0.2095 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | F1              | out_of_domain |    47 |  0.2527 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | F1              | OVERALL       |    89 |  0.2323 | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | HalluRate       | in_domain     |    42 |  0.119  | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | HalluRate       | out_of_domain |    47 |  0.0851 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | HalluRate       | OVERALL       |    89 |  0.1011 | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Rouge-L         | in_domain     |    42 |  0.0394 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Rouge-L         | out_of_domain |    47 |  0.0676 | default |
+-------------+------------+-----------------+---------------+-------+---------+---------+
| model       | tool_bench | Rouge-L         | OVERALL       |    89 |  0.0543 | -       |
+-------------+------------+-----------------+---------------+-------+---------+---------+

Use this model

with llama-cli

llama-cli -m Qwen3-4B-toolcall.Q4_K_M.gguf

with ollama

edit a makefile named(Qwen3-4B-toolcall.Q4_K_M.txt) like:

FROM ./Qwen3-4B-toolcall.Q4_K_M
TEMPLATE """<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

then create a model using ollama
ollama create Qwen3-4B-toolcall.Q4_K_M -f Qwen3-4B-toolcall.Q4_K_M.txt
then run it
ollama run Qwen3-4B-toolcall.Q4_K_M

Downloads last month: 32

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for wesjos/Qwen3-4B-toolcall-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

unsloth/Qwen3-4B-unsloth-bnb-4bit

Quantized

(36)

this model