What are the hardware requirements for MiniMax M2.5 NVFP4?

MiniMax M2.5 NVFP4 requires approximately 140.1 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 NVFP4 and how large is it?

MiniMax M2.5 NVFP4 is developed by nvidia, a model with 116.3b 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 NVFP4?

MiniMax M2.5 NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniMax M2.5 NVFP4 by nvidia — VRAM 140.1GB, 192K context

Name: MiniMax M2.5 NVFP4
Author: nvidia

MiniMax M2.5 NVFP4 is an open-source language model by nvidia. Features: 116.3b LLM, VRAM: 140.1GB, Context: 192K, License: other, LLM Explorer Score: 0.3.

8-bit Base model:minimaxai/minimax-m... Base model:quantized:minimaxai... Conversational Custom code Minimax Minimax m2 Model optimizer Modelopt Nvfp4 Nvidia Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/MiniMax-M2.5-NVFP4

MiniMax M2.5 NVFP4 Parameters and Internals

LLM Name	MiniMax M2.5 NVFP4
Repository 🤗	https://huggingface.co/nvidia/MiniMax-M2.5-NVFP4
Base Model(s)	MiniMaxAI/MiniMax-M2.5 MiniMaxAI/MiniMax-M2.5
Model Size	116.3b
Required VRAM	140.1 GB
Updated	2026-07-31
Maintainer	nvidia
Model Type	minimax_m2
Model Files	5.0 GB: 1-of-29 5.0 GB: 2-of-29 5.0 GB: 3-of-29 5.0 GB: 4-of-29 5.0 GB: 5-of-29 5.0 GB: 6-of-29 5.0 GB: 7-of-29 5.0 GB: 8-of-29 5.0 GB: 9-of-29 5.0 GB: 10-of-29 5.0 GB: 11-of-29 5.0 GB: 12-of-29 5.0 GB: 13-of-29 5.0 GB: 14-of-29 5.0 GB: 15-of-29 5.0 GB: 16-of-29 5.0 GB: 17-of-29 5.0 GB: 18-of-29 5.0 GB: 19-of-29 5.0 GB: 20-of-29 5.0 GB: 21-of-29 5.0 GB: 22-of-29 5.0 GB: 23-of-29 5.0 GB: 24-of-29 5.0 GB: 25-of-29 5.0 GB: 26-of-29 5.0 GB: 27-of-29 3.9 GB: 28-of-29 1.2 GB: 29-of-29
Model Architecture	MiniMaxM2ForCausalLM
License	other
Context Length	196608
Model Max Length	196608
Transformers Version	4.57.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	200064

Rank the MiniMax M2.5 NVFP4 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

Best Alternatives to MiniMax M2.5 NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
MiniMax M2.7 MXFP4	200K / 127.4 GB	938	1
MiniMax M2.7 NVFP4	192K / 139.7 GB	45794	66
MiniMax M2.1 MXFP4	192K / 127.4 GB	13381	1
MiniMax M2.5 MXFP4	192K / 127.4 GB	131	1

Note: green Score (e.g. "73.2") means that the model is better than nvidia/MiniMax-M2.5-NVFP4.