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

Use Docker

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

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

Unsloth Studio

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

How to use novelaide/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 novelaide/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": "novelaide/Qwen3-Reranker-8B-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use novelaide/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 novelaide/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 "novelaide/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"

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

Lemonade

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

Pull the model

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

Run Hermes

hermes

Atomic Chat

Qwen3 Reranker 8B Q4_K_M GGUF

This repository contains the exact immutable local-model asset used by NovelAide. This GGUF is a NovelAide-built derived artifact produced from the official Safetensors checkpoint. It is not an official Qwen GGUF release.

Provenance

Base model: Qwen/Qwen3-Reranker-8B
Asset source: Qwen/Qwen3-Reranker-8B
Pinned source revision: 77d193c791ed757ca307ee72715aa132723da912
Runtime: llama-cpp
NovelAide asset ID: qwen3-reranker-8b
NovelAide CDN prefix: qwen3-reranker-8b-gguf/456176c855aba6e6

The base model and conversion input are the official Qwen/Qwen3-Reranker-8B Safetensors at immutable revision 77d193c791ed757ca307ee72715aa132723da912.

NovelAide converts that checkpoint to BF16 GGUF and then quantizes it to Q4_K_M with ggml-org/llama.cpp tag b9842, commit 6f4f53f2b7da54fcdbbecaaa734337c337ad6176. This is the llama.cpp revision embedded by the Desktop runtime's node-llama-cpp@3.19.0.

The resulting GGUF is a NovelAide-built derived asset, not an upstream Qwen GGUF. Its immutable content-addressed object prefix is qwen3-reranker-8b-gguf/456176c855aba6e6; it must not overwrite the previously published community-derived artifact.

Files

File	Size	SHA-256
`Qwen3-Reranker-8B-Q4_K_M.gguf`	4460.17 MiB	`456176c855aba6e6cc23335fbf285bdb41f77f9e4e5eeb2e72077749482c3b89`

Usage

Use the GGUF files with a compatible llama.cpp runtime and the ONNX files with a compatible ONNX / Transformers.js runtime. NovelAide pins the exact files and checksums shown above; do not substitute similarly named quantizations.

License and attribution

The model asset follows the upstream apache-2.0 license. Review the linked base model and asset source model cards for their complete terms, limitations, and attribution requirements. NovelAide is not affiliated with or endorsed by the upstream model authors.

Downloads last month: 153

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

Text Ranking

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

Model tree for novelaide/Qwen3-Reranker-8B-Q4_K_M-GGUF

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-Reranker-8B

Quantized

(48)

this model