Instructions to use cortexso/qwen3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cortexso/qwen3 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 cortexso/qwen3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/qwen3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cortexso/qwen3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/qwen3: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 cortexso/qwen3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/qwen3: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 cortexso/qwen3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/qwen3:Q4_K_M

Use Docker

docker model run hf.co/cortexso/qwen3:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/qwen3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/qwen3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/qwen3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/qwen3:Q4_K_M

Ollama
How to use cortexso/qwen3 with Ollama:
```
ollama run hf.co/cortexso/qwen3:Q4_K_M
```

Unsloth Studio

How to use cortexso/qwen3 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 cortexso/qwen3 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 cortexso/qwen3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/qwen3 to start chatting

How to use cortexso/qwen3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cortexso/qwen3: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": "cortexso/qwen3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use cortexso/qwen3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cortexso/qwen3: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 "cortexso/qwen3: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 cortexso/qwen3 with Docker Model Runner:
```
docker model run hf.co/cortexso/qwen3:Q4_K_M
```

Lemonade

How to use cortexso/qwen3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/qwen3:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use cortexso/qwen3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cortexso/qwen3: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 cortexso/qwen3:Q4_K_M

Run Hermes

hermes

Atomic Chat

qwen3 / README.md

Minh141120

Update README.md

d25d099 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

3.22 kB

	---
	license: apache-2.0
	pipeline_tag: text-generation
	tags:
	- cortex.cpp
	- featured
	---

	## Overview

	Qwen Team developed and released the Qwen3 series, a state-of-the-art family of language models optimized for advanced reasoning, dialogue, instruction-following, and agentic use cases. Qwen3 introduces innovative thinking/non-thinking mode switching, long context capabilities, and multilingual support, all while achieving high efficiency and performance.

	The Qwen3 models span several sizes and include support for seamless reasoning, complex tool usage, and detailed multi-turn conversations, making them ideal for applications such as research assistants, code generation, enterprise chatbots, and more.

	## Variants

	### Qwen3

	\| No \| Variant \| Branch \| Cortex CLI command \|
	\|----\|--------------------------------------------------------------------------------------------\|--------\|-------------------------------\|
	\| 1 \| [Qwen3-0.6B](https://huggingface.co/cortexso/qwen3/tree/0.6b) \| 0.6b \| `cortex run qwen3:0.6b` \|
	\| 2 \| [Qwen3-1.7B](https://huggingface.co/cortexso/qwen3/tree/1.7b) \| 1.7b \| `cortex run qwen3:1.7b` \|
	\| 3 \| [Qwen3-4B](https://huggingface.co/cortexso/qwen3/tree/4b) \| 4b \| `cortex run qwen3:4b` \|
	\| 4 \| [Qwen3-8B](https://huggingface.co/cortexso/qwen3/tree/8b) \| 8b \| `cortex run qwen3:8b` \|
	\| 5 \| [Qwen3-14B](https://huggingface.co/cortexso/qwen3/tree/14b) \| 14b \| `cortex run qwen3:14b` \|
	\| 6 \| [Qwen3-32B](https://huggingface.co/cortexso/qwen3/tree/32b) \| 32b \| `cortex run qwen3:32b` \|
	\| 7 \| [Qwen3-30B-A3B](https://huggingface.co/cortexso/qwen3/tree/30b-a3b) \| 30b-a3b\| `cortex run qwen3:30b-a3b` \|

	Each branch contains multiple quantized GGUF versions:
	- Qwen3-0.6B: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0
	- Qwen3-1.7B: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0
	- Qwen3-4B: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0
	- Qwen3-8B: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0
	- Qwen3-32B: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0
	- Qwen3-30B-A3B: *q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0

	## Use it with Jan (UI)

	1. Install Jan using [Quickstart](https://jan.ai/docs/quickstart)
	2. Use in Jan model Hub:
	```bash
	cortexso/qwen3
	```

	## Use it with Cortex (CLI)

	1. Install Cortex using [Quickstart](https://cortex.jan.ai/docs/quickstart)
	2. Run the model with command:
	```bash
	cortex run qwen3
	```

	## Credits

	- Author: Qwen Team
	- Converter: [Menlo Research](https://menlo.ai/)
	- Original License: [License](https://www.apache.org/licenses/LICENSE-2.0)
	- Blogs: [Qwen3: Think Deeper, Act Faster](https://qwenlm.github.io/blog/qwen3/)