What are the hardware requirements for MoEv2?

MoEv2 requires approximately 14.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MoEv2 and how large is it?

MoEv2 is developed by jeiku, a model with 4b 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 MoEv2?

MoEv2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MoEv2 by jeiku — VRAM 14.5GB, 128K context

Name: MoEv2
Author: jeiku

MoEv2 is an open-source language model by jeiku. Features: 4b LLM, VRAM: 14.5GB, Context: 128K, LLM Explorer Score: 0.16.

Mixtral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jeiku/MoEv2

MoEv2 Parameters and Internals

LLM Name	MoEv2
Repository 🤗	https://huggingface.co/jeiku/MoEv2
Model Size	4b
Required VRAM	14.5 GB
Updated	2026-06-09
Maintainer	jeiku
Model Type	mixtral
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MixtralForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|begin_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the MoEv2 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 MoEv2

Best Alternatives	Context / RAM	Downloads	Likes
MIA 4B	2K / 6.8 GB	5	1