Instructions to use RedHatAI/Qwen3-32B-speculator.eagle3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3-32B-speculator.eagle3 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Qwen3-32B-speculator.eagle3", trust_remote_code=True)

# Load model directly
from transformers import Eagle3Speculator
model = Eagle3Speculator.from_pretrained("RedHatAI/Qwen3-32B-speculator.eagle3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Qwen3-32B-speculator.eagle3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3-32B-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/Qwen3-32B-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3-32B-speculator.eagle3

SGLang

How to use RedHatAI/Qwen3-32B-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/Qwen3-32B-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/Qwen3-32B-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/Qwen3-32B-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/Qwen3-32B-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Qwen3-32B-speculator.eagle3 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3-32B-speculator.eagle3
```

Using this speculator with Red Hat AI's quantized model

by nebula0248 - opened Nov 24, 2025

Discussion

nebula0248

Nov 24, 2025

Does this speculator work with RedHatAI/Qwen3-32B-FP8-dynamic? I used this speculator with the 16-bit quantized Qwen3-32B, and it worked well with an acceptance length of 2–3. However, it fails with RedHatAI/Qwen3-32B-FP8-dynamic: the main model isn’t accepting the speculator’s predicted tokens. Is this expected behavior? I assumed that even with quantization, the token prediction distribution should be very close to the unquantized model.

RelaxingSnorlax

Red Hat AI org Jan 16

•

edited Jan 16

Hi @nebula0248 ,

Thank you for reporting this. We have conducted a performance audit to investigate the reported drop in acceptance length when using the RedHatAI/Qwen3-32B-speculator.eagle3 with the RedHatAI/Qwen3-32B-FP8-dynamic verifier.

Using vLLM main(commit 6ca4f400d), our internal benchmarks show that the quantized verifier actually maintains—and in some cases slightly exceeds—the performance of the BF16 base model.

Evaluation Results

We ran a side-by-side comparison between the base configuration and the FP8-dynamic verifier using a standard evaluation suite.

Metric	Base Model (`Qwen/Qwen3-32B`)	Quantized Verifier (`RedHatAI/...-FP8-dynamic`)
Avg. Drafted Tokens	18,119.62	22,581.43
Weighted Acceptance Rates	`[0.705, 0.476, 0.313]`	`[0.714, 0.492, 0.333]`
Conditional Acceptance Rates	`[0.705, 0.675, 0.657]`	`[0.714, 0.689, 0.678]`

Technical Analysis

Our data indicates that the RedHatAI/Qwen3-32B-speculator.eagle3 is highly robust to the FP8-dynamic quantization of the target verifier. Since we are seeing stable acceptance rates in our environment (2x H100), the performance drop you observed might be related to specific serving parameters, memory pressure, or hardware-specific kernels.

To help us narrow this down, could you please provide:

Your GPU hardware (e.g., A100, H100, etc.).
The exact vllm serve command you are using.
Your vLLM version or specific commit.

We are closing this for now based on our verification results, but please feel free to share your logs and re-open this if you continue to see regressions!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment