Downloads · 30 days
64
29% of all-time downloads
Qwen3-8B-ToolACE-speculator.eagle3
kenkaneki/Qwen3-8B-ToolACE-speculator.eagle3
Qwen3-8B-ToolACE-speculator.eagle3 is a machine learning model from kenkaneki. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Fine-tuned EAGLE-3 speculative decoding draft head for tool-calling workloads.
All-time downloads
224
Public
Parameters
1B
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 100%
Parameter types
How the weights are stored.
BF161B · 100%
Base models
Datasets
Model card
From the Hugging Face model README
Qwen3-8B ToolACE EAGLE-3 Speculator
Fine-tuned EAGLE-3 speculative decoding draft head for tool-calling workloads.
Base
- Target model: kenkaneki/Qwen3-8B-ToolACE
- Draft base: RedHatAI/Qwen3-8B-speculator.eagle3
- Fine-tuning data: Team-ACE/ToolACE (3000 samples, 1 epoch)
- Framework: speculators
Results (H100, ToolACE prompts)
| Metric (c=1) | BF16 baseline | + EAGLE3 FT | Speedup |
|---|---|---|---|
| E2EL p50 | 323.9 ms | 175.4 ms | 1.85x |
| Output tok/s | 150.4 | 271.3 | 1.80x |
| TTFT p50 | 15.5 ms | 18.7 ms | 0.83x |
EAGLE-3 is lossless: output is identical to the target model by construction. No quality loss.
Validation accuracy
- Token 0: 82.2% (vs 61.9% trained from scratch on ToolACE-only)
- Token 1: 63.6% (vs 38.7%)
- Token 2: 49.2% (vs 24.0%)
Usage with vLLM
vllm serve kenkaneki/Qwen3-8B-ToolACE \
--speculative-config '{"model":"kenkaneki/Qwen3-8B-ToolACE-speculator.eagle3","num_speculative_tokens":3,"method":"eagle3"}' \
--enable-auto-tool-choice --tool-call-parser hermes
Training
python scripts/finetune_eagle.py
Hardware: NVIDIA H100 80GB
- License
- apache-2.0
- Created
- Mar 19, 2026
- Updated
- Mar 20, 2026