README.md

---
license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
- speculative-decoding
- eagle3
- draft-model
- minimax-m3
- amd-quark
- vllm
base_model:
- amd/MiniMax-M3-MXFP4
---

# MiniMax-M3-EAGLE3.1

## Model Overview

* **Model Architecture:** `LlamaForCausalLMEagle3` (EAGLE3 speculative-decoding draft model)
  * **Input:** Text
  * **Output:** Text
* **Draft variant:** EAGLE3.1 (single decoder layer, full vocabulary, BF16)
* **Target model:** [amd/MiniMax-M3-MXFP4](https://huggingface.co/amd/MiniMax-M3-MXFP4)
* **Supported Hardware Microarchitecture:** AMD Instinct MI350X / MI355X
* **Inference Engine:** vLLM (ROCm)
* **Trained by:** the AMD Quark team

**MiniMax-M3-EAGLE3.1** is an EAGLE3 draft model for accelerating inference of
[amd/MiniMax-M3-MXFP4](https://huggingface.co/amd/MiniMax-M3-MXFP4) with speculative
decoding. It was trained **from scratch (cold-start)** entirely on AMD Instinct
MI350X GPUs with a vLLM-centric pipeline (on-policy data generated by the target,
hidden-state extraction from the target, and in-loop serve-evaluation). Speculative
decoding is **lossless** — every draft token is verified by the target, so the
target's output distribution is preserved.

## Intended Use

This model is intended to be used as an EAGLE3 draft model for speculative decoding
with [amd/MiniMax-M3-MXFP4](https://huggingface.co/amd/MiniMax-M3-MXFP4) as the
target model. It reuses the target's tokenizer, so no tokenizer files are shipped
with the draft.

## Acceptance Length

Evaluated on the official **SPEED-Bench** harness with `num_speculative_tokens=3`
and temperature 0. Acceptance length (AL) is the mean number of tokens accepted per
target verification step (AL = 1 means no speedup); higher is better.

### Acceptance length by domain (SPEED-Bench qualitative)

| Domain        | Acceptance length (AL) |
| ------------- | ---------------------- |
| Coding        | 3.32                   |
| Math          | 3.14                   |
| RAG           | 3.12                   |
| Multilingual  | 3.04                   |
| Reasoning     | 2.89                   |
| STEM          | 2.86                   |
| Summarization | 2.86                   |
| Humanities    | 2.71                   |
| QA            | 2.55                   |
| Writing       | 2.33                   |
| Roleplay      | 2.01                   |
| **Overall**   | **2.80**               |

### Acceptance length by context length

| Context length | Acceptance length (AL) |
| -------------- | ---------------------- |
| 1K             | 2.69                   |
| 8K             | 2.70                   |
| 16K            | 2.69                   |
| 32K            | 2.65                   |

Acceptance length stays essentially flat from 1K to 32K context.

## Serving with vLLM

Serve the [amd/MiniMax-M3-MXFP4](https://huggingface.co/amd/MiniMax-M3-MXFP4) target
with this draft as the EAGLE3 speculative model (single AMD Instinct MI355X node,
TP=8). See the [target model card](https://huggingface.co/amd/MiniMax-M3-MXFP4) for
the ROCm/vLLM runtime image and setup.

```bash
export VLLM_ROCM_USE_AITER=1

vllm serve amd/MiniMax-M3-MXFP4 \
  --trust-remote-code \
  --tensor-parallel-size 8 \
  --block-size 128 \
  --attention-backend TRITON_ATTN \
  --moe-backend emulation \
  --speculative-config '{"method":"eagle3","model":"amd/MiniMax-M3-EAGLE3.1","num_speculative_tokens":3,"attention_backend":"TRITON_ATTN"}'
```

## Citation and Acknowledgements

Trained by the AMD Quark team as the EAGLE3 draft for
[amd/MiniMax-M3-MXFP4](https://huggingface.co/amd/MiniMax-M3-MXFP4). Please validate
quality and acceptance length in your own serving stack.

## License

This draft targets MiniMax-M3; see the bundled `MiniMax M3 LICENSE.txt` (MiniMax Community License) for the terms that apply to the target model and its derivatives.

Modifications Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.