What are the hardware requirements for TeenyTinyLlama 460M?

TeenyTinyLlama 460M requires approximately 1.9 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TeenyTinyLlama 460M and how large is it?

TeenyTinyLlama 460M is developed by nicholasKluge, a model with 460m 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 TeenyTinyLlama 460M?

TeenyTinyLlama 460M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TeenyTinyLlama 460M by nicholasKluge — VRAM 1.9GB, 2K context

Name: TeenyTinyLlama 460M
Author: nicholasKluge

TeenyTinyLlama 460M is an open-source language model by nicholasKluge. Features: 460m LLM, VRAM: 1.9GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.11.

Arxiv:2401.16640 Co2 eq emissions Dataset:nicholaskluge/pt-corpu... Endpoints compatible Instruct Jax Llama Model-index Pt Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m

TeenyTinyLlama 460M Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

Research

Primary Use Cases:

Developing language models for low-resource languages

Limitations:

Not suitable for human-facing interactions, Not intended for deployment, Limited to Brazilian Portuguese

Considerations:

Users should conduct risk and bias assessment before any real-world application

Additional Notes

Pre-trained model released under Apache 2.0; comprehensive evaluations available.

Supported Languages

Portuguese (high)

Training Details

Data Sources:

Pt-Corpus Instruct (6.2B tokens)

Data Volume:

6.2B tokens

Methodology:

Transformer-based model pre-trained via causal language modeling

Context Length:

2048

Training Time:

~ 280 hours

Hardware Used:

1 NVIDIA A100-SXM4-40GB

Model Architecture:

Transformer

Input Output

Input Format:

Tokenizer input as text for generation

Accepted Modalities:

text

Output Format:

Generated text

Performance Tips:

Review repetition penalty settings to avoid verbosity and repetition

LLM Name	TeenyTinyLlama 460M
Repository 🤗	https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m
Model Size	460m
Required VRAM	1.9 GB
Updated	2026-07-08
Maintainer	nicholasKluge
Model Type	llama
Instruction-Based	Yes
Model Files	1.9 GB 3.8 GB 1.9 GB 0.0 GB
Supported Languages	pt
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the TeenyTinyLlama 460M 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

Quantized Models of the TeenyTinyLlama 460M

Model	Likes	Downloads	VRAM
TeenyTinyLlama 460M Chat AWQ	1	4	0 GB
TeenyTinyLlama 460M AWQ	1	3	0 GB

Best Alternatives to TeenyTinyLlama 460M

Best Alternatives	Context / RAM	Downloads	Likes
TeenyTinyLlama 460M Chat	2K / 0 GB	90	3
...60M Experimental Ptbr Instruct	2K / 0.9 GB	8	4
TeenyTinyLlama 460M Chat AWQ	2K / 0.3 GB	4	1
TeenyTinyLlama 460M AWQ	2K / 0.3 GB	3	1

Note: green Score (e.g. "73.2") means that the model is better than nicholasKluge/TeenyTinyLlama-460m.