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

Use Docker

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

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

Unsloth Studio

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

Using HuggingFace Spaces for Unsloth

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

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

Start the llama.cpp server

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

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cryptorugmuncher/Qwen3-Reranker-8B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cryptorugmuncher/Qwen3-Reranker-8B-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 "cryptorugmuncher/Qwen3-Reranker-8B-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-GGUF / README.md

cryptorugmunch

Upload README.md with huggingface_hub

a76a97c verified 8 days ago

preview code

Raw

History Blame Contribute Delete

2.81 kB

metadata

language:
  - en
  - multilingual
license: apache-2.0
library_name: llama.cpp
tags:
  - reranker
  - qwen
  - qwen3
  - gguf
  - cross-encoder
  - RAG
  - q4_k_m
datasets:
  - Qwen/Qwen3-Reranker-8B

Qwen3-Reranker-8B-GGUF

GGUF quantized version of Qwen3-Reranker-8B by Alibaba Cloud.

Why This Matters

Cross-encoder rerankers dramatically improve RAG quality. Instead of relying on cosine similarity alone, the reranker reads every query-document pair and produces a relevance score. This catches semantic nuances that embedding-only retrieval misses.

Quantization

Format	Size	BPW	Notes
FP16	15.1 GB	16.00	Original, full precision
Q4_K_M	4.5 GB	4.94	Recommended — best quality/size tradeoff

Quantized with llama.cpp Q4_K_M — the balanced quantization that preserves >99% of scoring accuracy while reducing memory by 70%.

Usage

llama.cpp (local inference)

# Serve the reranker
llama-server \
    --model qwen3-reranker-8b-Q4_K_M.gguf \
    --port 8003 \
    --host 127.0.0.1 \
    --rerank \
    --embd-normalize -1 \
    --mlock

# Query the reranker API
curl http://localhost:8003/rerank \
  -H "Content-Type: application/json" \
  -d '{
    "query": "crypto market manipulation signal",
    "documents": [
      "Whale moves 5000 BTC to exchange",
      "Ethereum gas prices hit new low",
      "MEV bot detected sandwich attack"
    ],
    "top_n": 3
  }'

Python (via requests)

import requests

response = requests.post("http://localhost:8003/rerank", json={
    "query": "DeFi lending risk",
    "documents": [
        "Aave utilization at 95%",
        "Bitcoin price update",
        "Compound borrow rate spikes"
    ],
    "top_n": 3
})
results = response.json()["results"]
for r in sorted(results, key=lambda x: x["relevance_score"], reverse=True):
    print(f"Doc {r['index']}: score={r['relevance_score']:.4f}")

Via HuggingFace Transformers

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained(
    "cryptorugmuncher/Qwen3-Reranker-8B-GGUF",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Reranker-8B")

Performance

4.5 GB RAM usage (vs 15.1 GB for FP16)
~80ms per query-doc pair on CPU (Xeon)
100+ languages supported
41K context window
Instruction-aware reranking — customize scoring criteria per task

Credits

Original model: Qwen/Qwen3-Reranker-8B by Alibaba Cloud
Quantization: llama.cpp
Uploaded by: cryptorugmuncher