Instructions to use RedHatAI/Qwen3-8B-Thinking-speculator.eagle3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3-8B-Thinking-speculator.eagle3 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Qwen3-8B-Thinking-speculator.eagle3", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RedHatAI/Qwen3-8B-Thinking-speculator.eagle3", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Qwen3-8B-Thinking-speculator.eagle3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3-8B-Thinking-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/Qwen3-8B-Thinking-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3-8B-Thinking-speculator.eagle3

SGLang

How to use RedHatAI/Qwen3-8B-Thinking-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/Qwen3-8B-Thinking-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/Qwen3-8B-Thinking-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/Qwen3-8B-Thinking-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/Qwen3-8B-Thinking-speculator.eagle3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Qwen3-8B-Thinking-speculator.eagle3 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3-8B-Thinking-speculator.eagle3
```

Qwen3-8B-Thinking-speculator.eagle3

Model Overview

Verifier: Qwen3-8B
Speculative Decoding Algorithm: EAGLE-3
Model Architecture: Eagle3Speculator
Release Date: 3/12/2026
Version: 1.0
Model Developers: RedHat

This is a speculator model designed for use with Qwen3-8B, 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 enabled. This model should be used with the Qwen3-8B chat template, specifically through the /chat/completions endpoint.

Use with vLLM

vllm serve Qwen/Qwen3-8B \
  -tp 1 \
  --speculative-config '{
    "model": "RedHatAI/Qwen3-8B-Thinking-speculator.eagle3",
    "num_speculative_tokens": 5,
    "method": "eagle3"
  }'

Acceptance lengths (draft length)

Dataset	k=1	k=2	k=3	k=4	k=5
HumanEval	1.83	2.43	2.90	3.23	3.42
math_reasoning	1.85	2.53	3.04	3.44	3.74
qa	1.77	2.30	2.67	2.90	3.11
question	1.80	2.37	2.78	3.12	3.31
rag	1.77	2.30	2.69	2.94	3.11
summarization	1.70	2.15	2.42	2.59	2.69
translation	1.74	2.25	2.59	2.81	2.93

Details

Configuration

Model: Qwen3-8B-Thinking-speculator.eagle3
temperature: 0.0
backend: vLLM chat_completions
rate-type: throughput
max-seconds per run: 300
hardware: 8× GPU (tensor parallel 8)
Benchmark data: RedHatAI/speculator_benchmarks
vLLM serve: --no-enable-prefix-caching, --max-num-seqs 64, --enforce-eager

Command

GUIDELLM__PREFERRED_ROUTE="chat_completions" \
GUIDELLM__MAX_CONCURRENCY=128 \
guidellm benchmark \
  --target "http://localhost:8000/v1" \
  --data "RedHatAI/speculator_benchmarks" \
  --data-args '{"data_files": "HumanEval.jsonl"}' \
  --rate-type throughput \
  --max-seconds 300 \
  --backend-args '{"extra_body": {"chat_completions": {"temperature": 0.0}}}'

Downloads last month: 41

Safetensors

Model size

1B params

Tensor type

I64

BF16

BOOL

Paper for RedHatAI/Qwen3-8B-Thinking-speculator.eagle3

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Paper • 2503.01840 • Published Mar 3, 2025 • 10