What are the hardware requirements for Mamba 130M?

Mamba 130M requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mamba 130M and how large is it?

Mamba 130M is developed by ArthurZ, a model with 130m 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 Mamba 130M?

Mamba 130M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mamba 130M by ArthurZ — VRAM 0.5GB

Name: Mamba 130M
Author: ArthurZ

Mamba 130M is an open-source language model by ArthurZ. Features: 130m LLM, VRAM: 0.5GB, LLM Explorer Score: 0.12.

Endpoints compatible Mamba Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ArthurZ/mamba-130m

Mamba 130M Parameters and Internals

Model Type

text generation

Input Output

Input Format:

Tokenized text input

Accepted Modalities:

text

Output Format:

Generated text

LLM Name	Mamba 130M
Repository 🤗	https://huggingface.co/ArthurZ/mamba-130m
Model Size	130m
Required VRAM	0.5 GB
Updated	2026-08-24
Maintainer	ArthurZ
Model Type	mamba
Model Files	0.5 GB
Model Architecture	MambaForCausalLM
Transformers Version	4.38.0.dev0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50280
Torch Data Type	float32

Rank the Mamba 130M 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 Mamba 130M

Best Alternatives	Context / RAM	Downloads	Likes
Mamba 130M Hf	0K / 0.5 GB	723007	72
PULI HuBA Mamba 130M	0K / 0.5 GB	7	3
...amba 130M Hf Finetuned Epitope	0K / 0.5 GB	7	0
Mamba 130M	0K / 0.5 GB	76	12

Note: green Score (e.g. "73.2") means that the model is better than ArthurZ/mamba-130m.