What are the hardware requirements for Zenz V3.1 Small?

Zenz V3.1 Small requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Zenz V3.1 Small and how large is it?

Zenz V3.1 Small is developed by Miwa-Keita, a model with 90.5m 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 Zenz V3.1 Small?

Zenz V3.1 Small is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Zenz V3.1 Small by Miwa-Keita — VRAM 0.2GB

Name: Zenz V3.1 Small
Author: Miwa-Keita

Zenz V3.1 Small is an open-source language model by Miwa-Keita. Features: 90.5m LLM, VRAM: 0.2GB, License: cc-by-sa-4.0, LLM Explorer Score: 0.21.

Gpt2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Miwa-Keita/zenz-v3.1-small

Zenz V3.1 Small Parameters and Internals

LLM Name	Zenz V3.1 Small
Repository 🤗	https://huggingface.co/Miwa-Keita/zenz-v3.1-small
Model Size	90.5m
Required VRAM	0.2 GB
Updated	2026-10-19
Maintainer	Miwa-Keita
Model Type	gpt2
Model Files	0.2 GB
Model Architecture	GPT2LMHeadModel
License	cc-by-sa-4.0
Transformers Version	4.30.0
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	[UNK]
Vocabulary Size	6000
Torch Data Type	float32
Activation Function	gelu_new
Errors	replace

Rank the Zenz V3.1 Small 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 Zenz V3.1 Small

Best Alternatives	Context / RAM	Downloads	Likes
Zenz V2.5 Small	0K / 0.2 GB	55	1