# Inco AI open-sources a DFlash 2 drafter for MiniMax M3.1 Flash

> Original title: MiniMax M3.1 Flash is out, and we've open-sourced a DFlash 2 drafter for it under Apache 2.0. It makes generation up to 3.5× faster, and ...

- Source: X search: AI open-source releases
- Published: 2026-10-23T02:01:22.000Z
- Bad Influence: https://badinfluence.news/items/kizwrj69m81ldb2xmmuteszdo
- Original: https://x.com/inco_ai/status/2113450678245056795

## Summary

Inco AI says it has open-sourced a DFlash 2 drafter for MiniMax M3.1 Flash under Apache 2.0. The company claims the drafter makes generation up to 3.5 times faster while remaining lossless.

## Why it matters

The post names the drafter's license and the speedup and losslessness claims, which help readers judge whether it fits their own MiniMax M3.1 Flash deployment.

## Post

MiniMax M3.1 Flash is out, and we've open-sourced a DFlash 2 drafter for it under Apache 2.0. It makes generation up to 3.5× faster, and it's lossless. Congrats to @MiniMax_AI on the release!

https://huggingface.co/incoai/MiniMax-M3.1-Flash-DFlash2

## Quoted post @MiniMax_AI

> MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token.
> 
> Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
> Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency.
> 
> Hugging Face:
> https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash
> ModelScope:
> https://modelscope.cn/models/MiniMax/MiniMax-M3.1-Flash
> 
> API: http://platform.minimax.io
> M Plan: https://minimax.io/m-planMiniMax
> MCode for desktop: https://agent.minimax.io/download

https://x.com/MiniMax_AI/status/2113436864904610008