What are the hardware requirements for TinyLLama V0?

TinyLLama V0 requires a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TinyLLama V0 and how large is it?

TinyLLama V0 is developed by Maykeye, a model with 4.6m 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 TinyLLama V0?

TinyLLama V0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TinyLLama V0 by Maykeye — 2K context

Name: TinyLLama V0
Author: Maykeye

TinyLLama V0 is an open-source language model by Maykeye. Features: 4.6m LLM, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.15.

Endpoints compatible Llama Onnx Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Maykeye/TinyLLama-v0

TinyLLama V0 Parameters and Internals

Model Type

Causal Language Model

Additional Notes

Extremely PoC version with simplified training and caching mechanics. Backup and validation scripts provided. Training data constraints exist due to context length handling.

Training Details

Data Sources:

TinyStoriesV2-GPT4-train.txt, TinyStoriesV2-GPT4-valid.txt

Methodology:

Training truncates stories longer than context size without sliding window. Uses open_llama_3b tokenizer.

Training Time:

9 hours total, 3 hours per epoch

Hardware Used:

40GB A100 GPU with ~30GB VRAM

Model Architecture:

Llama

Release Notes

Version:

1.0

Notes:

First version PoC with basic function to train and validate with specified dataset files.

LLM Name	TinyLLama V0
Repository 🤗	https://huggingface.co/Maykeye/TinyLLama-v0
Model Size	4.6m
Required VRAM	0 GB
Updated	2026-08-08
Maintainer	Maykeye
Model Type	llama
Model Files	0.0 GB 0.0 GB
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.30.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the TinyLLama V0 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 TinyLLama V0

Best Alternatives	Context / RAM	Downloads	Likes
SimpleLlamaSentences	2K / 0 GB	6	0
UniversalNER TinyLLama	2K / 0 GB	10	1
UniversalNER TinyLLama	2K / 0 GB	6	1
Q4 Llama 3	8K / 6.1 GB	12	0
Llama3 Finetune 4bit	8K / 6.1 GB	0	0