What are the hardware requirements for Lorde Tiny Aya?

Lorde Tiny Aya requires approximately 6.7 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lorde Tiny Aya and how large is it?

Lorde Tiny Aya is developed by Oxlino, a model with 3.3b 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 Lorde Tiny Aya?

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

Lorde Tiny Aya by Oxlino — VRAM 6.7GB, 8K context

Name: Lorde Tiny Aya
Author: Oxlino

Lorde Tiny Aya is an open-source language model by Oxlino. Features: 3.3b LLM, VRAM: 6.7GB, Context: 8K, License: cc-by-nc-4.0, LLM Explorer Score: 0.28.

Aligntune Ar Auditkit Base model:coherelabs/tiny-aya... Base model:finetune:coherelabs... Cohere2 Conversational Curatorkit Data-curation Dataset:oxlino/lorde-data En Endpoints compatible Es Fr Hi Id Lexsi-hackathon Llm-judge Non-commercial Pt Region:us Safetensors Tiny-aya Tr

Model Card on HF 🤗: https://huggingface.co/Oxlino/lorde-tiny-aya

Lorde Tiny Aya Parameters and Internals

LLM Name	Lorde Tiny Aya
Repository 🤗	https://huggingface.co/Oxlino/lorde-tiny-aya
Base Model(s)	CohereLabs/tiny-aya-global CohereLabs/tiny-aya-global
Model Size	3.3b
Required VRAM	6.7 GB
Updated	2026-11-13
Maintainer	Oxlino
Model Type	cohere2
Model Files	6.7 GB
Supported Languages	en hi fr ar es pt id tr
Model Architecture	Cohere2ForCausalLM
License	cc-by-nc-4.0
Context Length	8192
Model Max Length	8192
Transformers Version	5.22.2
Tokenizer Class	TokenizersBackend
Padding Token	<PAD>
Vocabulary Size	262144

Rank the Lorde Tiny Aya 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 Lorde Tiny Aya

Best Alternatives	Context / RAM	Downloads	Likes
Shadowwork Shift Plain Sft	488K / 13.5 GB	31	0
... Aya Global Esa Grpo Safe V3.1	8K / 6.7 GB	91	0
...ya Global Esa Grpo Esc Safe V2	8K / 6.7 GB	117	0
...ya Global Safetypulse Repaired	8K / 6.7 GB	51	1
Tiny Aya Global Hindi SFT	8K / 6.7 GB	46	0
...rth Langsafe Circuit Merge 0p5	8K / 6.7 GB	26	0
... Aya 3.3B L2 Thinker BF16 GGUF	4882K / 6.7 GB	974	1

Note: green Score (e.g. "73.2") means that the model is better than Oxlino/lorde-tiny-aya.