Qwen3-Reranker-4B-GGUF-llama_cpp

Instructions to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp 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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M

Use Docker

docker model run hf.co/ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M

LM Studio
Jan
Ollama
How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with Ollama:
```
ollama run hf.co/ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
```

Unsloth Studio

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp 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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp 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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp to start chatting

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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": "ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with Docker Model Runner:
```
docker model run hf.co/ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M
```

Lemonade

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-Reranker-4B-GGUF-llama_cpp-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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 ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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 "ebasKing/Qwen3-Reranker-4B-GGUF-llama_cpp: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-4B-GGUF-llama_cpp / README.md

ebasKing

Duplicate from Voodisss/Qwen3-Reranker-4B-GGUF-llama_cpp

ffe7913 16 days ago

preview code

Raw

History Blame Contribute Delete

4.14 kB

	---
	base_model: Qwen/Qwen3-Reranker-4B
	library_name: gguf
	license: apache-2.0
	pipeline_tag: text-ranking
	tags:
	- reranker
	- gguf
	- llama.cpp
	- qwen3
	- text-ranking
	---

	# Qwen3-Reranker-4B — GGUF (llama.cpp)

	Working GGUF of [Qwen/Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) for [llama.cpp](https://github.com/ggml-org/llama.cpp). Converted 2025-03-09 with the official `convert_hf_to_gguf.py`.

	> Other sizes: [0.6B](https://huggingface.co/Voodisss/Qwen3-Reranker-0.6B-GGUF-llama_cpp) · [4B (this)](https://huggingface.co/Voodisss/Qwen3-Reranker-4B-GGUF-llama_cpp) · [8B](https://huggingface.co/Voodisss/Qwen3-Reranker-8B-GGUF-llama_cpp)

	## Quantization quality comparison (Qwen3-Reranker-4B)

	Benchmarked on [MTEB AskUbuntuDupQuestions](https://huggingface.co/datasets/mteb/AskUbuntuDupQuestions) (361 queries) via llama-server `/v1/rerank` on RTX 3090. All quants produced from the same F16 source using `llama-quantize`.

	\| Quant \| Size \| NDCG@10 \| MAP@10 \| MRR@10 \| Δ NDCG@10 \|
	\| ------ \| ------- \| ------- \| ------ \| ------ \| --------- \|
	\| F16 \| 7.50 GB \| 0.7003 \| 0.5530 \| 0.7711 \| baseline \|
	\| Q8_0 \| 3.99 GB \| 0.6985 \| 0.5514 \| 0.7670 \| -0.3% \|
	\| Q6_K \| 3.08 GB \| 0.7016 \| 0.5548 \| 0.7722 \| +0.2% \|
	\| Q5_K_M \| 2.69 GB \| 0.7009 \| 0.5517 \| 0.7699 \| +0.1% \|
	\| Q5_0 \| 2.63 GB \| 0.6995 \| 0.5532 \| 0.7676 \| -0.1% \|
	\| Q4_K_M \| 2.33 GB \| 0.7058 \| 0.5596 \| 0.7746 \| +0.8% \|
	\| Q4_0 \| 2.21 GB \| 0.6930 \| 0.5426 \| 0.7623 \| -1.1% \|
	\| Q3_K_M \| 1.93 GB \| 0.7040 \| 0.5555 \| 0.7828 \| +0.5% \|
	\| Q2_K \| 1.55 GB \| 0.6691 \| 0.5079 \| 0.7401 \| -4.5% \|

	Takeaway: All quants from Q8_0 down to Q3_K_M are within ±1% of F16 — pick based on your VRAM budget. Q4_K_M (2.33 GB) is the sweet spot: 3.2x smaller than F16 with no measurable quality loss. Avoid Q2_K — it's the only quant with real degradation.
	## Does it work?

	Yes. Most community GGUFs of Qwen3-Reranker produce garbage scores (`4.5e-23`) because they're missing reranker-specific tensors. See [llama.cpp #16407](https://github.com/ggml-org/llama.cpp/issues/16407). This one works:

	```
	Doc 0 (relevant): relevance_score = 0.999966
	Doc 1 (irrelevant): relevance_score = 0.000069
	```

	## Quick start

	```bash
	llama-server -m Qwen3-Reranker-4B-f16.gguf --reranking --pooling rank --embedding --port 8081
	```

	```bash
	curl http://localhost:8081/v1/rerank \
	-H "Content-Type: application/json" \
	-d '{
	"query": "employment termination notice period",
	"documents": [
	"The Labour Code requires 30 calendar days written notice.",
	"Corporate tax rates for small enterprises."
	]
	}'
	```

	Use `/v1/rerank`, not `/v1/embeddings`. The embeddings endpoint returns zeros for reranker models.

	## What's different about this GGUF?

	The official `convert_hf_to_gguf.py` detects Qwen3-Reranker and does things naive converters skip:

	- Extracts `cls.output.weight` (the yes/no classifier) from `lm_head`
	- Sets `pooling_type = RANK` metadata
	- Bakes in the rerank chat template
	- Sets `classifier.output_labels = ["yes", "no"]`

	Without these, llama-server has nothing to compute scores from.

	## Known broken GGUFs

	- [DevQuasar/Qwen.Qwen3-Reranker-4B-GGUF](https://huggingface.co/DevQuasar/Qwen.Qwen3-Reranker-4B-GGUF) — confirmed broken with llama.cpp

	## models.ini example

	```ini
	[Qwen3-Reranker-4B-f16]
	model = /path/to/Qwen3-Reranker-4B-f16.gguf
	reranking = true
	pooling = rank
	embedding = true
	ctx-size = 32768
	```

	For a full multi-model setup guide (embedding + reranking + chat on one server), see the [llama-server Qwen3 guide](https://gist.github.com/VooDisss/42bce4eb5c76d3c325633886c5e348ee).

	## Convert it yourself

	```bash
	pip install huggingface_hub gguf torch safetensors sentencepiece
	python -c "from huggingface_hub import snapshot_download; snapshot_download('Qwen/Qwen3-Reranker-4B', local_dir='Qwen3-Reranker-4B-src')"
	python convert_hf_to_gguf.py --outtype f16 --outfile Qwen3-Reranker-4B-f16.gguf Qwen3-Reranker-4B-src/
	```

	## License

	Apache 2.0 — same as the [original model](https://huggingface.co/Qwen/Qwen3-Reranker-4B).