Quantized version of nebius/EAGLE3-gpt-oss-20b.
Their model card is pasted as is below.
Files:
- model.safetensors - original unquantized safetensors
- model.gguf - unquantized bf16 GGUF
- EAGLE3-gpt-oss-20b.gguf - GGUF quantized to Q5_K_M
Model Description
This is an EAGLE-3 draft-model for gpt-oss-20b, trained from scratch using LK losses — training objectives that directly target acceptance rate rather than using KL divergence as a proxy.
Training Details
- Base model: openai/gpt-oss-20b
- Draft architecture: EAGLE-3
- Training data: Infinity-Instruct-0625 with gpt-oss-20b generated responses
- Training objective: Hybrid LK loss with adaptive λ scheduling (η=3)
- Training: 10 epochs from random initialization
- Draft length: K = 6 speculative tokens
Performance
Average acceptance length (τ) measured across MT-bench, HumanEval, and GSM8K with K = 7:
| Configuration | Temperature = 0 | Temperature = 1 |
|---|---|---|
| EAGLE-3 + KL | 3.46 | 3.17 |
| EAGLE-3 + LK (ours) | 3.49 | 3.29 |
Comparison with Public Checkpoints
| Model | MT-bench (τ) | HumanEval (τ) | GSM8K (τ) |
|---|---|---|---|
| RedHatAI/gpt-oss-20b-speculator.eagle3 | 2.63 | 2.43 | 3.00 |
| Ours | 3.20 | 3.01 | 3.65 |
Measured at temperature = 1 with K = 7
Note: Earlier vLLM versions sampled draft tokens greedily regardless of temperature, which underestimated acceptance rates at temperature > 0. Stochastic draft sampling was introduced in v0.18.0, and from v0.21.0 it can be enabled via
speculative_configusingrejection_sample_methodanddraft_sample_method. The acceptance metrics reported above were measured under standard rejection sampling and are reproducible with the configuration below.
Usage with vLLM
from vllm import LLM, SamplingParams
llm = LLM(
model="openai/gpt-oss-20b",
speculative_config={
"method": "eagle3",
"model": "nebius/EAGLE3-gpt-oss-20b",
"num_speculative_tokens": 6,
"rejection_sample_method": "standard",
"draft_sample_method": "gumbel",
},
)
sampling_params = SamplingParams(temperature=0.7)
outputs = llm.generate(["Explain speculative decoding in simple terms."], sampling_params)
License
Citation
@misc{samarin2026lklosses,
title = {LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding},
author = {Alexander Samarin and Sergei Krutikov and Anton Shevtsov and Sergei Skvortsov and Filipp Fisin and Alexander Golubev},
year = {2026},
eprint = {2602.23881},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2602.23881}
}