What are the hardware requirements for Kyro 29M?

Kyro 29M requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kyro 29M and how large is it?

Kyro 29M is developed by Astrosully, a model with 29m 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 Kyro 29M?

Kyro 29M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kyro 29M by Astrosully — VRAM 0.1GB

Name: Kyro 29M
Author: Astrosully

Kyro 29M is an open-source language model by Astrosully. Features: 29m LLM, VRAM: 0.1GB, License: apache-2.0.

Autoresearch Dataset:huggingfacefw/fineweb-... Dataset:huggingfacetb/finemath Dataset:huggingfacetb/smollm-c... Dataset:wikimedia/wikipedia En From-scratch Kyro Model-index Muon Pytorch Region:us Safetensors Small-language-model Tiny-llm

Model Card on HF 🤗: https://huggingface.co/Astrosully/Kyro-29M

Kyro 29M Parameters and Internals

LLM Name	Kyro 29M
Repository 🤗	https://huggingface.co/Astrosully/Kyro-29M
Model Size	29m
Required VRAM	0.1 GB
Updated	2026-11-04
Maintainer	Astrosully
Model Type	kyro
Model Files	0.1 GB
Supported Languages	en
Model Architecture	Kyro
License	apache-2.0
Model Max Length	512
Tokenizer Class	tiktoken
Vocabulary Size	16384
Torch Data Type	float32

Rank the Kyro 29M 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