CMB-Qwen3-32B-Eagle3

Model Overview

• Verifier: Qwen/Qwen3-32B
• Speculative Decoding Algorithm: EAGLE-3
• Model Architecture: LlamaForCausalLMEagle3
• Release Date: 03/31/2026
• Version: 1.0
• Model Developers: Architecture Management Team, Information Technology Department, China Merchants Bank (CMB)

This is a speculator model designed for use with Qwen/Qwen3-32B, based on the EAGLE-3 speculative decoding algorithm. It was trained by Architecture Management Team, Information Technology Department, China Merchants Bank (CMB). The training data is a combination of Chinese and English open-source datasets, with data synthesis and cleaning performed on the original datasets. The following are the sources of the original training data:

1. swift/Chinese-Qwen3-235B-Thinking-2507-Distill-data-110k-SFT
2. a-m-team/AM-Qwen3-Distilled

This model should be used with the Qwen/Qwen3-32B chat template, specifically through the /chat/completions endpoint.

Use with sglang

python3 -m sglang.launch_server \
  --model Qwen/Qwen3-32B \
  --speculative-algorithm EAGLE3 \
  --speculative-draft-model-path <our-model-path> \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 3

Use with vLLM

It is important to note that when using vLLM, you need to enable the model configuration file for vLLM, which named config_vllm.json. Before entering the following commands, you need to rename the file from config_vllm.json to config.json to make it effective.

vllm serve Qwen/Qwen3-32B \
  -tp 2 \
  --speculative-config '{
    "model": <our-model-path>,
    "num_speculative_tokens": 3,
    "method": "eagle3"
  }'

Evaluations

Use cases

Use Case	Dataset	Samples
Coding	HumanEval	168
Math Reasoning	gsm8k	80
English Text Summarization	CNN/Daily Mail	80
Chinese Mixed	HC3-Chinese	120
Chinese Finance	HC3-Chinese	80
Chinese Text Summarization	LCSTS	80

Acceptance lengths

Use Case	draft_tokens_num=3
Coding	2.11
Math Reasoning	2.60
English Text Summarization	1.95
Chinese Mixed	2.08
Chinese Finance	2.15
Chinese Text Summarization	2.05

Details

Configuration

• temperature: 0.6
• top_p: 0.95
• top_k: 20
• repetitions: 3
• hardware: 2xH800