RedHatAI/Qwen3-32B-speculator.eagle3

Qwen3-32B-speculator.eagle3

Model Overview

• —Verifier: Qwen/Qwen3-32B
• —Speculative Decoding Algorithm: EAGLE-3
• —Model Architecture: Eagle3Speculator
• —Release Date: 09/17/2025
• —Version: 1.0
• —Model Developers: RedHat

This is a speculator model designed for use with Qwen/Qwen3-32B, based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Aeala/ShareGPT_Vicuna_unfiltered and the train_sft split of HuggingFaceH4/ultrachat_200k datasets. This model should be used with the Qwen/Qwen3-32B chat template, specifically through the /chat/completions endpoint.

Use with vLLM

vllm serve Qwen/Qwen3-32B \
  -tp 2 \
  --speculative-config '{
    "model": "RedHatAI/Qwen3-32B-speculator.eagle3",
    "num_speculative_tokens": 3,
    "method": "eagle3"
  }'

Evaluations

<h3>Use cases</h3> <table> <thead> <tr> <th>Use Case</th> <th>Dataset</th> <th>Number of Samples</th> </tr> </thead> <tbody> <tr> <td>Coding</td> <td>HumanEval</td> <td>168</td> </tr> <tr> <td>Math Reasoning</td> <td>gsm8k</td> <td>80</td> </tr> <tr> <td>Text Summarization</td> <td>CNN/Daily Mail</td> <td>80</td> </tr> </tbody> </table>

<h3>Acceptance lengths</h3> <table> <thead> <tr> <th>Use Case</th> <th>k=1</th> <th>k=2</th> <th>k=3</th> <th>k=4</th> <th>k=5</th> <th>k=6</th> <th>k=7</th> </tr> </thead> <tbody> <tr> <td>Coding</td> <td>1.67</td> <td>2.06</td> <td>2.29</td> <td>2.39</td> <td>2.47</td> <td>2.50</td> <td>2.53</td> </tr> <tr> <td>Math Reasoning</td> <td>1.73</td> <td>2.21</td> <td>2.49</td> <td>2.69</td> <td>2.80</td> <td>2.83</td> <td>3.08</td> </tr> <tr> <td>Text Summarization</td> <td>1.62</td> <td>1.95</td> <td>2.15</td> <td>2.23</td> <td>2.27</td> <td>2.32</td> <td>2.33</td> </tr> </tbody> </table>

<h3>Performance benchmarking (2xA100)</h3> <div style="display: flex; justify-content: center; gap: 20px;">

<figure style="text-align: center;"> <img src="assets/Qwen3-32B-HumanEval.png" alt="Coding" width="100%"> </figure>

<figure style="text-align: center;"> <img src="assets/Qwen3-32B-math_reasoning.png" alt="Math Reasoning" width="100%"> </figure>

<figure style="text-align: center;"> <img src="assets/Qwen3-32B-summarization.png" alt="Text Summarization" width="100%"> </figure> </div>

<details> <summary>Details</summary> <strong>Configuration</strong>

• —temperature: 0.6
• —top_p: 0.95
• —top_k: 20
• —repetitions: 3
• —time per experiment: 10min
• —hardware: 2xA100
• —vLLM version: 0.11.0
• —GuideLLM version: 0.3.0

<strong>Command</strong>

GUIDELLM__PREFERRED_ROUTE="chat_completions" \
guidellm benchmark \
  --target "http://localhost:8000/v1" \
  --data "RedHatAI/speculator_benchmarks" \
  --data-args '{"data_files": "HumanEval.jsonl"}' \
  --rate-type sweep \
  --max-seconds 600 \
  --output-path "Qwen3-32B-HumanEval.json" \
  --backend-args '{"extra_body": {"chat_completions": {"temperature":0.6, "top_p":0.95, "top_k":20}}}'

GuideLLM interface changed, so for compatibility with the latest version (v0.6.0), please use the following command:

GUIDELLM__PREFERRED_ROUTE="chat_completions" \
guidellm benchmark \
  --target "http://localhost:8000/v1" \
  --data "RedHatAI/speculator_benchmarks" \
  --data-args '{"data_files": "HumanEval.jsonl"}' \
  --profile sweep \
  --max-seconds 1800 \
  --output-path "my_output.json" \
  --backend-args '{"extras": {"body": {"temperature":0.6, "top_p":0.95, "top_k":20}}}'

</details>