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

Libraries

How to use cortexso/small-thinker with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/small-thinker",
	filename="smallthinker-3b-preview-q2_k.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cortexso/small-thinker 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/small-thinker:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/small-thinker: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/small-thinker:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/small-thinker: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/small-thinker:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/small-thinker: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/small-thinker:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/small-thinker:Q4_K_M

Use Docker

docker model run hf.co/cortexso/small-thinker:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/small-thinker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/small-thinker"
# 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/small-thinker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/small-thinker:Q4_K_M

Ollama
How to use cortexso/small-thinker with Ollama:
```
ollama run hf.co/cortexso/small-thinker:Q4_K_M
```

Unsloth Studio

How to use cortexso/small-thinker 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/small-thinker 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/small-thinker to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use cortexso/small-thinker with Docker Model Runner:
```
docker model run hf.co/cortexso/small-thinker:Q4_K_M
```

Lemonade

How to use cortexso/small-thinker with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.small-thinker-Q4_K_M

List all available models

lemonade list

Minh141120 commited on Jan 24, 2025

Commit

42ca266

verified ·

1 Parent(s): 484f38f

Create README.md

Browse files

Files changed (1) hide show

README.md +36 -0

README.md ADDED Viewed

	@@ -0,0 +1,36 @@

+---
+license: mit
+---
+## Overview
+**PowerInfer** developed and released the [SmallThinker-3B-preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview), a fine-tuned version of the Qwen2.5-3B-Instruct model. SmallThinker is optimized for efficient deployment on resource-constrained devices while maintaining high performance in reasoning, coding, and general text generation tasks. It outperforms its base model on key benchmarks, including AIME24, AMC23, and GAOKAO2024, making it a robust tool for both edge deployment and as a draft model for larger systems like QwQ-32B-Preview.
+SmallThinker was fine-tuned in two phases using high-quality datasets, including PowerInfer/QWQ-LONGCOT-500K and PowerInfer/LONGCOT-Refine-500K. Its small size allows for up to 70% faster inference speeds compared to larger models, making it ideal for applications requiring quick responses and efficient computation.
+## Variants
+| No | Variant | Cortex CLI command |
+| --- | --- | --- |
+| 1 | [gguf](https://huggingface.co/cortexso/small-thinker) | `cortex run small-thinker` |
+## Use it with Jan (UI)
+1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
+2. Use in Jan model Hub:
+    ```text
+    cortexso/small-thinker
+    ```
+## 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 small-thinker
+    ```
+## Credits
+- **Author:** PowerInfer
+- **Converter:** [Homebrew](https://www.homebrew.ltd/)
+- **Original License:** [License](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview/blob/main/LICENSE)