MiniMax-Text-01

A hybrid MoE using Lightning Attention, with 456B total and 45.9B active parameters, trained at 1M context and extrapolatable to 4M.

LegacyLanguageOpen weights

MODEL NUMBER245

Specifications

Only published specifications are shown.

Total parameters

456B

Active parameters

45.9B

Architecture

Hybrid

Context

Input modalities

Text

Output modalities

Text

Open weights

Yes

Status

Legacy

A hybrid MoE using Lightning Attention, with 456B total and 45.9B active parameters, trained at 1M context and extrapolatable to 4M.

Lightning AttentionSoftmax Attention

Long context

2025-01-15Open weights

MiniMax-Text-01 released model weights.

Select a card to view the related model.