What are the hardware requirements for Veyra2 30M Base 2B Tokens?

Veyra2 30M Base 2B Tokens 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 Veyra2 30M Base 2B Tokens and how large is it?

Veyra2 30M Base 2B Tokens is developed by veyra-ai, a model with 2b 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 Veyra2 30M Base 2B Tokens?

Veyra2 30M Base 2B Tokens is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Veyra2 30M Base 2B Tokens by veyra-ai — VRAM 0.1GB, 1K context

Name: Veyra2 30M Base 2B Tokens
Author: veyra-ai

Veyra2 30M Base 2B Tokens is an open-source language model by veyra-ai. Features: 2b LLM, VRAM: 0.1GB, Context: 1K, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

Dataset:codeparrot/github-code... Dataset:huggingfaceh4/ultracha... Dataset:huggingfacetb/smollm-c... En Endpoints compatible English Gguf Gguf-compatible Llama Local-ai Quantized Region:us Safetensors Small-language-model Veyra

Model Card on HF 🤗: https://huggingface.co/veyra-ai/veyra2-30m-base-2b-tokens

Veyra2 30M Base 2B Tokens Parameters and Internals

LLM Name	Veyra2 30M Base 2B Tokens
Repository 🤗	https://huggingface.co/veyra-ai/veyra2-30m-base-2b-tokens
Model Size	2b
Required VRAM	0.1 GB
Updated	2026-06-01
Maintainer	veyra-ai
Model Type	llama
Model Files	0.1 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	4.46.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	8192
Torch Data Type	bfloat16

Rank the Veyra2 30M Base 2B Tokens 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 Veyra2 30M Base 2B Tokens

Best Alternatives	Context / RAM	Downloads	Likes
...inicpm5 2B Distilled Reasoning	128K / 5 GB	770	1
Aitana 2B S Base	8K / 4.5 GB	559	1
Aitana 2B S Tourism Base	8K / 4.5 GB	221	0
HelpingAI2.5 2B	8K / 1.1 GB	70	2
HelpingAI2.5 2B	8K / 1.1 GB	19	2
MiniCPM5 2B 8bit	128K / 2.7 GB	734	6
MiniCPM5 2B OptiQ 4bit	128K / 1.9 GB	317	3
MiniCPM5 2B Mlx 4Bit	128K / 1.4 GB	286	1
MiniCPM5 2B MLX 8bit	128K / 2.7 GB	193	3
MiniCPM5 2B MLX 6bit	128K / 2 GB	192	1

Note: green Score (e.g. "73.2") means that the model is better than veyra-ai/veyra2-30m-base-2b-tokens.