Downloads · 30 days
135
0% of all-time downloads
Qwen3-235B-A22B-EAGLE3
lmsys/Qwen3-235B-A22B-EAGLE3
Qwen3-235B-A22B-EAGLE3 is a machine learning model from lmsys. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
The Eagle3 draft model was trained using the SpecForge framework for the Qwen3-235B-A22B model, leveraging a combination of UltraChat and ShareGPT datasets.
All-time downloads
30.8K
Public
Parameters
1.2B
2.4 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
Parameter types
How the weights are stored.
BF161.2B · 100%
Model card
From the Hugging Face model README
sglang-EAGLE3-Qwen3-235B-A22B
Model Introduction
The Eagle3 draft model was trained using the SpecForge framework for the Qwen3-235B-A22B model, leveraging a combination of UltraChat and ShareGPT datasets.
Benchmark Results
- gsm8k (200 questions)
Output throughput: 224.168 token/s
<b>Accept length: 3.538</b>
- mtbench (80 questions)
Output throughput: 241.5 token/s
<b>Accept length: 3.019</b>
Usage
You can use this Eagle3 draft model in SGLang with the following command:
python3 -m sglang.launch_server \
--model <Qwen3-235B-A22B> \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path <EAGLE3-Qwen3-235B-A22B> \
--speculative-num-steps 5 \
--speculative-eagle-topk 8 \
--speculative-num-draft-tokens 32 \
--mem-fraction-static 0.75 \
--tp 8 \
--enable-ep-moe \
--context-length 8192 \
--trust-remote-code \
--host 0.0.0.0 \
--port 30000 \
--dtype bfloat16
- Library
- transformers
- Type
- llama
- License
- mit
- Created
- Jul 28, 2025
- Updated
- Jul 28, 2025