Instructions to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3

SGLang

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3
```

Qwen3-8B-speculator.eagle3

Model Overview

Verifier: Qwen3-30B-A3B-Instruct-2507
Speculative Decoding Algorithm: EAGLE-3
Model Architecture: Eagle3Speculator
Release Date: 12/12/2025
Version: 1.0
Model Developers: RedHat

This is a speculator model designed for use with Qwen3-30B-A3B-Instruct-2507 , based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Magpie-Align/Magpie-Pro-300K-Filtered and the HuggingFaceH4/ultrachat_200k datasets. The model was trained with thinking turned disabled. This model should be used with the Qwen3-30B-A3B-Instruct-2507 chat template, specifically through the /chat/completions endpoint.

Use with vLLM

vllm serve Qwen3-30B-A3B-Instruct-2507 \
  -tp 1 \
  --speculative-config '{
    "model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3",
    "num_speculative_tokens": 3,
    "method": "eagle3"
  }'

Evaluations

Use cases

Use Case	Dataset	Number of Samples
Coding	HumanEval	168
Math Reasoning	gsm8k	80
Text Summarization	CNN/Daily Mail	80

Acceptance lengths

Use Case	k=1	k=2	k=3	k=4	k=5
Coding	1.81	2.47	2.85	3.13	3.50
Math Reasoning	1.87	2.53	3.09	3.57	3.79
Text Summarization	1.58	1.90	2.08	2.16	2.24

Details

Configuration

Downloads last month: 813

Safetensors

Model size

0.5B params

Tensor type

I64

BF16

BOOL

Collection including RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3

Speculator Models

Collection

29 items • Updated 10 days ago • 24

Paper for RedHatAI/Qwen3-30B-A3B-Instruct-2507-speculator.eagle3

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Paper • 2503.01840 • Published Mar 3, 2025 • 10