What are the hardware requirements for Cosmo.0?

Cosmo.0 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 Cosmo.0 and how large is it?

Cosmo.0 is developed by DedeProGames, a model with 34.6m 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 Cosmo.0?

Cosmo.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Cosmo.0 by DedeProGames — VRAM 0.1GB, 1K context

Name: Cosmo.0
Author: DedeProGames

Cosmo.0 is an open-source language model by DedeProGames. Features: 34.6m LLM, VRAM: 0.1GB, Context: 1K, LLM Explorer Score: 0.31.

Conversational Dclm-edu Fineweb-edu Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/DedeProGames/cosmo.0

Cosmo.0 Parameters and Internals

LLM Name	Cosmo.0
Repository 🤗	https://huggingface.co/DedeProGames/cosmo.0
Model Size	34.6m
Required VRAM	0.1 GB
Updated	2026-10-07
Maintainer	DedeProGames
Model Type	llama
Model Files	0.1 GB
Model Architecture	LlamaForCausalLM
Context Length	1024
Model Max Length	1024
Transformers Version	5.10.2
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	8192

Rank the Cosmo.0 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 Cosmo.0

Best Alternatives	Context / RAM	Downloads	Likes
Dumb 1.2 Preview 0625	1K / 0.1 GB	5	0