Instructions to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF",
	filename="Qwen3-8B-speculator.eagle3-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

Use Docker

docker model run hf.co/williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

LM Studio
Jan

vLLM

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

Ollama
How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with Ollama:
```
ollama run hf.co/williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
```

Unsloth Studio

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-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 williamliao/Qwen3-8B-EAGLE3-Speculator-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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF to start chatting

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

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": "williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

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 "williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16" \
  --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 williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with Docker Model Runner:
```
docker model run hf.co/williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16
```

Lemonade

How to use williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3-8B-EAGLE3-Speculator-GGUF-F16

List all available models

lemonade list

Qwen3-8B EAGLE3 Speculator GGUF

This repository contains a GGUF conversion of RedHatAI/Qwen3-8B-speculator.eagle3 for use with llama.cpp EAGLE3 speculative decoding.

This is not a standalone chat model. It is an EAGLE3 draft/speculator model and must be used together with the matching target/verifier model.

Target model: Qwen/Qwen3-8B
Speculator source: RedHatAI/Qwen3-8B-speculator.eagle3
Runtime: llama.cpp with --spec-type draft-eagle3

Files

File	Type	Notes
`Qwen3-8B-speculator.eagle3-F16.gguf`	EAGLE3 speculator GGUF	Converted from the original RedHatAI safetensors checkpoint

Usage with llama.cpp

Example:

llama-server \
  -m Qwen3-8B-Q4_K_M.gguf \
  -md Qwen3-8B-speculator.eagle3-F16.gguf \
  --spec-type draft-eagle3 \
  --spec-draft-n-max 4 \
  --spec-draft-p-min 0.5 \
  -c 32768 \
  -ngl 99 \
  -fa on

Windows CMD example:

llama-server.exe ^
  -m Qwen3-8B-Q4_K_M.gguf ^
  -md Qwen3-8B-speculator.eagle3-F16.gguf ^
  --spec-type draft-eagle3 ^
  --spec-draft-n-max 4 ^
  --spec-draft-p-min 0.5 ^
  -c 32768 ^
  -ngl 99 ^
  -fa on

Important Notes

This GGUF file is only the draft/speculator model. You still need a compatible GGUF of the target model, such as a GGUF conversion or quantization of Qwen/Qwen3-8B.

Do not use this speculator with unrelated models such as Qwen3-14B, Qwen3-32B, Gemma, Llama, or Qwen3.6 models. EAGLE3 speculators are target-specific.

Tested Configuration

Tested with:

Runtime: llama.cpp with EAGLE3 support
Target model: Qwen3-8B GGUF
Draft model: this EAGLE3 GGUF
Example settings:
- --spec-type draft-eagle3
- --spec-draft-n-max 4
- --spec-draft-p-min 0.5

Local benchmark observations may vary depending on GPU, quantization, context length, batch size, and prompt type.

Benchmark Notes

In local testing, EAGLE3 showed stronger gains on structured or predictable outputs such as:

code generation
JSON output
repeated pattern generation
short factual responses

It was less effective on some tasks such as translation, creative writing, and long reasoning, where draft acceptance may be lower.

Conversion

Converted with llama.cpp convert_hf_to_gguf.py using the original speculator repository and the matching target model directory.

Example conversion command:

python convert_hf_to_gguf.py \
  RedHatAI/Qwen3-8B-speculator.eagle3 \
  --outtype f16 \
  --target-model-dir Qwen/Qwen3-8B \
  --outfile Qwen3-8B-speculator.eagle3-F16.gguf

PowerShell example:

python .\convert_hf_to_gguf.py `
  "E:\OLLAMA_MODELS\Qwen3-8B-speculator.eagle3" `
  --outtype f16 `
  --target-model-dir "E:\OLLAMA_MODELS\Qwen3-8B" `
  --outfile "E:\OLLAMA_MODELS\Qwen3-8B-speculator.eagle3-F16.gguf"

Credits

Original EAGLE3 speculator model by RedHatAI:

RedHatAI/Qwen3-8B-speculator.eagle3

Target model:

Qwen/Qwen3-8B

GGUF support and runtime:

ggml-org/llama.cpp

License

This repository is a converted GGUF version of the original speculator model. The original model license and usage terms apply. Please refer to the upstream repositories for full license details.

Downloads last month: 312

GGUF

Model size

1B params

Architecture

eagle3

Hardware compatibility

16-bit

Model tree for williamliao/Qwen3-8B-EAGLE3-Speculator-GGUF

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(333)

this model