What are the hardware requirements for MiniMax M2.7 4bit Mxfp4?

MiniMax M2.7 4bit Mxfp4 requires approximately 121.5 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 M2.7 4bit Mxfp4 and how large is it?

MiniMax M2.7 4bit Mxfp4 is developed by mlx-community, 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.

How does MiniMax M2.7 4bit Mxfp4 perform on standard benchmarks?

MiniMax M2.7 4bit Mxfp4 has the following published scores: LMSYS ELO 1404. Compare against reference models on this page or on the LLM Explorer leaderboards.

MiniMax M2.7 4bit Mxfp4 by mlx-community — VRAM 121.5GB, 192K context

Name: MiniMax M2.7 4bit Mxfp4
Author: mlx-community

MiniMax M2.7 4bit Mxfp4 is an open-source language model by mlx-community. Features: 228.7b LLM, VRAM: 121.5GB, Context: 192K, License: other, Quantized, LLM Explorer Score: 0.39, ELO: 1404.

4-bit 4bit Base model:minimaxai/minimax-m... Base model:quantized:minimaxai... Conversational Custom code Minimax m2 Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/MiniMax-M2.7-4bit-mxfp4

MiniMax M2.7 4bit Mxfp4 Benchmarks

LMSys ELO 1404 vs 1272 (so35) 10.4%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

MiniMax M2.7 4bit Mxfp4 Parameters and Internals

LLM Name	MiniMax M2.7 4bit Mxfp4
Repository 🤗	https://huggingface.co/mlx-community/MiniMax-M2.7-4bit-mxfp4
Base Model(s)	MiniMaxAI/MiniMax-M2.7 MiniMaxAI/MiniMax-M2.7
Model Size	228.7b
Required VRAM	121.5 GB
Updated	2026-08-07
Maintainer	mlx-community
Model Type	minimax_m2
Model Files	4.9 GB: 1-of-24 5.2 GB: 2-of-24 5.2 GB: 3-of-24 5.2 GB: 4-of-24 5.2 GB: 5-of-24 5.2 GB: 6-of-24 5.2 GB: 7-of-24 5.2 GB: 8-of-24 5.2 GB: 9-of-24 5.2 GB: 10-of-24 5.2 GB: 11-of-24 5.2 GB: 12-of-24 5.2 GB: 13-of-24 5.2 GB: 14-of-24 5.2 GB: 15-of-24 5.2 GB: 16-of-24 5.2 GB: 17-of-24 5.2 GB: 18-of-24 5.2 GB: 19-of-24 5.2 GB: 20-of-24 5.2 GB: 21-of-24 5.2 GB: 22-of-24 5.2 GB: 23-of-24 2.2 GB: 24-of-24
Quantization Type	4bit
Model Architecture	MiniMaxM2ForCausalLM
License	other
Context Length	196608
Model Max Length	196608
Transformers Version	4.46.1
Tokenizer Class	TokenizersBackend
Vocabulary Size	200064

Rank the MiniMax M2.7 4bit Mxfp4 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 M2.7 4bit Mxfp4

Best Alternatives	Context / RAM	Downloads	Likes
MiniMax M2.7 4bit	192K / 128.3 GB	739	2
MiniMax M2.7 3bit	192K / 99.7 GB	319	4
MiniMax M2.7 6bit	192K / 185.8 GB	268	1
MiniMax M2.7 8bit	192K / 228.2 GB	237	1
MiniMax M2.7 5bit	192K / 155.8 GB	189	2
MiniMax M2.7 8bit Gs32	192K / 211.8 GB	66	2
MiniMax M2 Mlx 8bit Gs32	192K / 206.5 GB	14	2
MiniMax M2.1 3bit	192K / 99.7 GB	3529	5
MiniMax M2.1 4bit	192K / 128.3 GB	2484	5
MiniMax M2.1 8bit	192K / 217.8 GB	2124	2