MiniMax-M3-MXFP8

Openintelligent123/MiniMax-M3-MXFP8

MiniMax-M3-MXFP8 is a image-text-to-text model from Openintelligent123. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

<div align="center" <img width="60%" src="figures/logo.svg" alt="MiniMax" </div <hr

Downloads · 30 days

100% of all-time downloads

All-time downloads

Public

Parameters

427B

444 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors444 GB · 100%

Parameter types

How the weights are stored.

F8_E4M3424B · 99%

Try a prompt

Base models

MiniMaxAI/MiniMax-M3

Model card

From the Hugging Face model README

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

Highlights:

Native Multimodality: M3 undergoes mixed-modality training from the very first step, enabling deeper semantic fusion across text, image, and video.
Context Scaling via Sparse Attention: M3 introduces MiniMax Sparse Attention (MSA) to improve long context efficiency. M3 delivers 9× prefill and 15× decode speedups compared to M2 at 1M context, reducing per-token compute to 1/20.
Coding & Cowork Capability: M3 achieves frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.

MiniMax-M3-MXFP8 is the MXFP8 quantized variant of MiniMax-M3, a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

MiniMax Sparse Attention (MSA)

M3 is powered by MiniMax Sparse Attention (MSA), a high-performance sparse attention operator designed for million-token contexts. Compared with GQA, MSA dramatically reduces the attention compute and memory footprint while preserving model quality.

📄 Read the technical report: arXiv:2606.13392 · Hugging Face Papers

How to Use

M3 supports three reasoning modes through the thinking parameter:

enabled — Reasoning is always enabled.
adaptive — M3 automatically determines when additional reasoning is beneficial.
disabled — Reasoning is disabled to minimize latency and maximize throughput.

Local Deployment

Download the model:

hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3

We recommend the following inference frameworks to serve the model:

Inference Parameters

We recommend the following parameters for best performance: temperature=1.0, top_p=0.95.

Contact Us

Task: Image-Text-to-Text
Library: transformers
Type: minimax_m3_vl
License: other
Created: Sep 6, 2026
Updated: Sep 6, 2026