What are the hardware requirements for Drakon 28M Base?

Drakon 28M Base requires approximately 0.2 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 Drakon 28M Base and how large is it?

Drakon 28M Base is developed by Squeal-Studio, a model with 28m 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 Drakon 28M Base?

Drakon 28M Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Drakon 28M Base by Squeal-Studio — VRAM 0.2GB, 1K context

Name: Drakon 28M Base
Author: Squeal-Studio

Drakon 28M Base is an open-source language model by Squeal-Studio. Features: 28m LLM, VRAM: 0.2GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.3.

Attention Convolutional Custom code Drakon Hybrid Mingru Pretrained Pytorch Recurrent Region:us Rnn Ru Russian Safetensors Small-language-model

Model Card on HF 🤗: https://huggingface.co/Squeal-Studio/drakon_28m-base

Drakon 28M Base Parameters and Internals

LLM Name	Drakon 28m Base
Repository 🤗	https://huggingface.co/Squeal-Studio/drakon_28m-base
Model Size	28m
Required VRAM	0.2 GB
Updated	2026-10-03
Maintainer	Squeal-Studio
Model Type	drakon
Model Files	0.2 GB
Supported Languages	ru
Model Architecture	DrakonForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Vocabulary Size	24001

Rank the Drakon 28M 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 Drakon 28M Base

Best Alternatives	Context / RAM	Downloads	Likes
Drakon 28m Instruct	1K / 0.1 GB	297	1

Note: green Score (e.g. "73.2") means that the model is better than Squeal-Studio/drakon_28m-base.