Instructions to use tensorblock/Light-R1-32B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/Light-R1-32B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/Light-R1-32B-GGUF",
	filename="Light-R1-32B-Q2_K.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 tensorblock/Light-R1-32B-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 tensorblock/Light-R1-32B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/Light-R1-32B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/Light-R1-32B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/Light-R1-32B-GGUF:Q2_K

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 tensorblock/Light-R1-32B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/Light-R1-32B-GGUF:Q2_K

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 tensorblock/Light-R1-32B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/Light-R1-32B-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/Light-R1-32B-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/Light-R1-32B-GGUF with Ollama:
```
ollama run hf.co/tensorblock/Light-R1-32B-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/Light-R1-32B-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 tensorblock/Light-R1-32B-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 tensorblock/Light-R1-32B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/Light-R1-32B-GGUF to start chatting

How to use tensorblock/Light-R1-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tensorblock/Light-R1-32B-GGUF:Q2_K

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": "tensorblock/Light-R1-32B-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tensorblock/Light-R1-32B-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 tensorblock/Light-R1-32B-GGUF:Q2_K

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 tensorblock/Light-R1-32B-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use tensorblock/Light-R1-32B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tensorblock/Light-R1-32B-GGUF:Q2_K

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 "tensorblock/Light-R1-32B-GGUF:Q2_K" \
  --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 tensorblock/Light-R1-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/Light-R1-32B-GGUF:Q2_K
```

Lemonade

How to use tensorblock/Light-R1-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/Light-R1-32B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Light-R1-32B-GGUF-Q2_K

List all available models

lemonade list

qihoo360/Light-R1-32B - GGUF

This repo contains GGUF format model files for qihoo360/Light-R1-32B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>

Model file specification

Filename	Quant type	File Size	Description
Light-R1-32B-Q2_K.gguf	Q2_K	12.313 GB	smallest, significant quality loss - not recommended for most purposes
Light-R1-32B-Q3_K_S.gguf	Q3_K_S	14.392 GB	very small, high quality loss
Light-R1-32B-Q3_K_M.gguf	Q3_K_M	15.935 GB	very small, high quality loss
Light-R1-32B-Q3_K_L.gguf	Q3_K_L	17.247 GB	small, substantial quality loss
Light-R1-32B-Q4_0.gguf	Q4_0	18.640 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Light-R1-32B-Q4_K_S.gguf	Q4_K_S	18.784 GB	small, greater quality loss
Light-R1-32B-Q4_K_M.gguf	Q4_K_M	19.851 GB	medium, balanced quality - recommended
Light-R1-32B-Q5_0.gguf	Q5_0	22.638 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Light-R1-32B-Q5_K_S.gguf	Q5_K_S	22.638 GB	large, low quality loss - recommended
Light-R1-32B-Q5_K_M.gguf	Q5_K_M	23.262 GB	large, very low quality loss - recommended
Light-R1-32B-Q6_K.gguf	Q6_K	26.886 GB	very large, extremely low quality loss
Light-R1-32B-Q8_0.gguf	Q8_0	34.821 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Light-R1-32B-GGUF --include "Light-R1-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Light-R1-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 44

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

Inference Providers NEW

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

Model tree for tensorblock/Light-R1-32B-GGUF

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Finetuned

qihoo360/Light-R1-32B

Quantized

(8)

this model