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