What are the hardware requirements for MiniCPM5 Aether?

MiniCPM5 Aether requires approximately 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 MiniCPM5 Aether and how large is it?

MiniCPM5 Aether is developed by aemmeath, a model with 2b 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 MiniCPM5 Aether?

MiniCPM5 Aether is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniCPM5 Aether by aemmeath — VRAM 5GB, 128K context

Name: MiniCPM5 Aether
Author: aemmeath

MiniCPM5 Aether is an open-source language model by aemmeath. Features: 2b LLM, VRAM: 5GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.31.

Base model:finetune:openbmb/mi... Base model:openbmb/minicpm5-2b Conversational En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/aemmeath/MiniCPM5-Aether

MiniCPM5 Aether Parameters and Internals

LLM Name	MiniCPM5 Aether
Repository 🤗	https://huggingface.co/aemmeath/MiniCPM5-Aether
Base Model(s)	MiniCPM5 2B openbmb/MiniCPM5-2B
Model Size	2b
Required VRAM	5 GB
Updated	2026-09-18
Maintainer	aemmeath
Model Type	llama
Model Files	5.0 GB: 0-of-1
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Tokenizer Class	TokenizersBackend
Padding Token	<unused_token_477>
Vocabulary Size	130560
Torch Data Type	bfloat16

Rank the MiniCPM5 Aether 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 MiniCPM5 Aether

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM5 2B Base	512K / 5 GB	54	17
MiniCPM5 2B	128K / 5 GB	2879	623
Huihui MiniCPM5 2B Abliterated	128K / 5 GB	310	8
MiniCPM5 2B MLX	128K / 1.4 GB	288	24
...iniCPM5 2B SFT Pashto Instruct	128K / 5 GB	1076	0
MiniCPM5 2B Abliterated	128K / 5 GB	531	0
MiniCPM5 2B Claude Fable5	128K / 5.1 GB	391	1
Uraion Forge 2B	128K / 5 GB	577	0
MiniCPM5 2B Heretic	128K / 5 GB	610	0
...iniCPM5 2B Heretic Abliterated	128K / 5 GB	510	1

Note: green Score (e.g. "73.2") means that the model is better than aemmeath/MiniCPM5-Aether.