What are the hardware requirements for MiniMax M2.5?

MiniMax M2.5 requires approximately 74 GB of VRAM and supports a context window of 192K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiniMax M2.5 and how large is it?

MiniMax M2.5 is developed by MiniMaxAI, a model with 228.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate MiniMax M2.5?

MiniMax M2.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniMax M2.5 by MiniMaxAI — VRAM 74GB, 192K context

Name: MiniMax M2.5
Author: MiniMaxAI

MiniMax M2.5 is an open-source language model by MiniMaxAI. Features: 228.7b LLM, VRAM: 74GB, Context: 192K, License: other, LLM Explorer Score: 0.43.

Conversational Custom code Deploy:azure Deploy:sagemaker Endpoints compatible Eval-results Fp8 Minimax m2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MiniMaxAI/MiniMax-M2.5

MiniMax M2.5 Parameters and Internals

LLM Name	MiniMax M2.5
Repository 🤗	https://huggingface.co/MiniMaxAI/MiniMax-M2.5
Model Size	228.7b
Required VRAM	74 GB
Updated	2026-08-04
Maintainer	MiniMaxAI
Model Type	minimax_m2
Model Files	3.7 GB: 0-of-126 1.2 GB: 1-of-126 2.5 GB: 2-of-126 1.2 GB: 3-of-126 2.5 GB: 4-of-126 1.2 GB: 5-of-126 2.5 GB: 6-of-126 1.2 GB: 7-of-126 2.5 GB: 8-of-126 1.2 GB: 9-of-126 2.5 GB: 10-of-126 1.2 GB: 11-of-126 2.5 GB: 12-of-126 1.2 GB: 13-of-126 2.5 GB: 14-of-126 1.2 GB: 15-of-126 2.5 GB: 16-of-126 1.2 GB: 17-of-126 2.5 GB: 18-of-126 1.2 GB: 19-of-126 2.5 GB: 20-of-126 1.2 GB: 21-of-126 2.5 GB: 22-of-126 1.2 GB: 23-of-126 2.5 GB: 24-of-126 1.2 GB: 25-of-126 2.5 GB: 26-of-126 1.2 GB: 27-of-126 2.5 GB: 28-of-126 1.2 GB: 29-of-126 2.5 GB: 30-of-126 1.2 GB: 31-of-126 2.5 GB: 32-of-126 1.2 GB: 33-of-126 2.5 GB: 34-of-126 1.2 GB: 35-of-126 2.5 GB: 36-of-126 1.2 GB: 37-of-126 2.5 GB: 38-of-126
Model Architecture	MiniMaxM2ForCausalLM
License	other
Context Length	196608
Model Max Length	196608
Transformers Version	4.46.1
Vocabulary Size	200064

Rank the MiniMax M2.5 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the MiniMax M2.5

Model	Likes	Downloads	VRAM
MiniMax M2.5 3bit	11	348	99 GB
MiniMax M2.5 4bit	3	265	128 GB
MiniMax M2.5 8bit	2	122	228 GB
MiniMax M2.5 6bit	4	104	185 GB
MiniMax M2.5 8bit Gs32	2	19	211 GB
MiniMax M2.5 5bit	1	17	155 GB

Best Alternatives to MiniMax M2.5

Best Alternatives	Context / RAM	Downloads	Likes
MiniMax M2.7	200K / 75.2 GB	923544	1235
List 3.0 Ultra Coder Brain	200K / 75.2 GB	22	10
MiniMax M2.7 BF16	200K / 147.3 GB	18	0
MiniMax M2	192K / 77.7 GB	103020	1492
MiniMax M2.7	192K / 213 GB	247	2
MiniMax M2.7	192K / 75.2 GB	58	18
MiniMax M2.5	192K / 75.2 GB	19	5
MiniMax M2.1	192K / 75.2 GB	54	13
MiniMax M2.1	192K / 77.7 GB	12798	1358
MiniMax M2	192K / 77.7 GB	24	17

Note: green Score (e.g. "73.2") means that the model is better than MiniMaxAI/MiniMax-M2.5.