Instructions to use sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF to start chatting

How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-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": "sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-Reranker-8B-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-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 sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sinjab/Qwen3-Reranker-8B-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sinjab/Qwen3-Reranker-8B-Q4_K_M-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 "sinjab/Qwen3-Reranker-8B-Q4_K_M-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"

Qwen3-Reranker-8B-Q4_K_M-GGUF / README.md

sinjab

Upload README.md with huggingface_hub

6a39653 verified 11 months ago

preview code

Raw

History Blame

1.94 kB

	---
	language:
	- en
	license: apache-2.0
	library_name: gguf
	tags:
	- reranker
	- gguf
	- llama.cpp
	base_model: Qwen/Qwen3-Reranker-8B
	---

	# Qwen3-Reranker-8B-Q4_K_M-GGUF

	This model was converted to GGUF format from [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) using llama.cpp via the ggml.ai's GGUF-my-repo space.

	Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-Reranker-8B) for more details on the model.

	## Model Information

	- Base Model: [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B)
	- Quantization: Q4_K_M
	- Format: GGUF (GPT-Generated Unified Format)
	- Converted with: llama.cpp

	## Quantization Details

	This is a Q4_K_M quantization of the original model:

	- F16: Full 16-bit floating point - highest quality, largest size
	- Q8_0: 8-bit quantization - high quality, good balance
	- Q4_K_M: 4-bit quantization with medium quality - smaller size, faster inference

	## Usage

	This model can be used with llama.cpp and other GGUF-compatible inference engines.

	```bash
	# Example using llama.cpp
	./llama-rerank -m Qwen3-Reranker-8B-Q4_K_M.gguf
	```

	## Model Files

	\| Quantization \| Use Case \|
	\|-------------\|----------\|
	\| F16 \| Maximum quality, largest size \|
	\| Q8_0 \| High quality, good balance of size/performance \|
	\| Q4_K_M \| Good quality, smallest size, fastest inference \|

	## Citation

	If you use this model, please cite the original model:

	```bibtex
	# See original model card for citation information
	```

	## License

	This model inherits the license from the original model. Please refer to the [original model card](https://huggingface.co/Qwen/Qwen3-Reranker-8B) for license details.

	## Acknowledgements

	- Original model by the authors of [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B)
	- GGUF conversion via llama.cpp by ggml.ai
	- Converted and uploaded by [sinjab](https://huggingface.co/sinjab)