What are the hardware requirements for Veyra 30M Base?

Veyra 30M Base requires approximately 0.1 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Veyra 30M Base and how large is it?

Veyra 30M Base is developed by veyra-ai, a model with 30m 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 Veyra 30M Base?

Veyra 30M Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Veyra 30M Base by veyra-ai — VRAM 0.1GB, 1K context

Name: Veyra 30M Base
Author: veyra-ai

Veyra 30M Base is an open-source language model by veyra-ai. Features: 30m LLM, VRAM: 0.1GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.25.

Base-model Conversational Dataset:huggingfacetb/cosmoped... En Endpoints compatible Llama Model-index Pytorch Region:us Safetensors Small-language-model Veyra

Model Card on HF 🤗: https://huggingface.co/veyra-ai/Veyra-30M-Base

Veyra 30M Base Parameters and Internals

LLM Name	Veyra 30M Base
Repository 🤗	https://huggingface.co/veyra-ai/Veyra-30M-Base
Model Size	30m
Required VRAM	0.1 GB
Updated	2026-08-04
Maintainer	veyra-ai
Model Type	llama
Model Files	0.1 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	5.10.2
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	8192
Torch Data Type	float32

Rank the Veyra 30M Base 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 Veyra 30M Base

Best Alternatives	Context / RAM	Downloads	Likes
TildeOpen 30B	64K / 60.9 GB	4576	165
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
Flash Llama 30M 20001	32K / 0.1 GB	134	0
Smaug Slerp 30B V0.1	32K / 60.4 GB	79	0
Tenebra 30B Alpha01	16K / 65 GB	50	16
Llama33b 16K	16K / 65.2 GB	1	1
Veyra2 Mango 30M Base	4K / 0.1 GB	0	5
Yayi2 30B Llama	4K / 121.2 GB	922	22
... Tokens By Perplexity Bottom K	4K / 5.4 GB	8	0
...via Sample With Temperature2.0	4K / 5.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than veyra-ai/Veyra-30M-Base.