What are the hardware requirements for MobileMoE M Base?

MobileMoE M Base requires approximately 5.7 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MobileMoE M Base and how large is it?

MobileMoE M Base is developed by ml-resources, a model with 2.8b 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 MobileMoE M Base?

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

MobileMoE M Base by ml-resources — VRAM 5.7GB, 8K context

Name: MobileMoE M Base
Author: ml-resources

MobileMoE M Base is an open-source language model by ml-resources. Features: 2.8b LLM, VRAM: 5.7GB, Context: 8K, License: fair-noncommercial-research-license, LLM Explorer Score: 0.31.

Arxiv:2605.27358 Custom code En Facebook Meta Mixture-of-experts Mobilemoe Moe On-device Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ml-resources/MobileMoE-M-Base

MobileMoE M Base Parameters and Internals

LLM Name	MobileMoE M Base
Repository 🤗	https://huggingface.co/ml-resources/MobileMoE-M-Base
Model Size	2.8b
Required VRAM	5.7 GB
Updated	2026-10-21
Maintainer	ml-resources
Model Type	mobilemoe
Model Files	3.0 GB: 1-of-2 2.7 GB: 2-of-2
Supported Languages	en
Model Architecture	MobileMoEForCausalLM
License	fair-noncommercial-research-license
Context Length	8192
Model Max Length	8192
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the MobileMoE M Base 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 MobileMoE M Base

Best Alternatives	Context / RAM	Downloads	Likes
MobileMoE L QAT	8K / 3 GB	289	1