What are the hardware requirements for Mamba2 2.7B?

Mamba2 2.7B requires approximately 5.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mamba2 2.7B and how large is it?

Mamba2 2.7B is developed by state-spaces, a model with 2.7b 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 Mamba2 2.7B?

Mamba2 2.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mamba2 2.7B by state-spaces — VRAM 5.4GB

Name: Mamba2 2.7B
Author: state-spaces

Mamba2 2.7B is an open-source language model by state-spaces. Features: 2.7b LLM, VRAM: 5.4GB, License: apache-2.0, LLM Explorer Score: 0.15.

Endpoints compatible Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/state-spaces/mamba2-2.7b

Mamba2 2.7B Parameters and Internals

LLM Name	Mamba2 2.7B
Repository 🤗	https://huggingface.co/state-spaces/mamba2-2.7b
Model Size	2.7b
Required VRAM	5.4 GB
Updated	2026-07-16
Maintainer	state-spaces
Model Files	5.4 GB
Model Architecture	AutoModel
License	apache-2.0
Vocabulary Size	50277

Rank the Mamba2 2.7B 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 Mamba2 2.7B

Best Alternatives	Context / RAM	Downloads	Likes
Cerebras GPT 2.7B	0K / 10.7 GB	1043	47
Vinallama Mental Health Q4	0K / 1.7 GB	17	0