What are the hardware requirements for Welmia 2.0 103M Base?

Welmia 2.0 103M Base requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Welmia 2.0 103M Base and how large is it?

Welmia 2.0 103M Base is developed by Welmia, a model with 103m 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 Welmia 2.0 103M Base?

Welmia 2.0 103M Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Welmia 2.0 103M Base by Welmia — VRAM 0.5GB

Name: Welmia 2.0 103M Base
Author: Welmia

Welmia 2.0 103M Base is an open-source language model by Welmia. Features: 103m LLM, VRAM: 0.5GB, License: apache-2.0, LLM Explorer Score: 0.33.

Custom-architecture Custom code En From-scratch Gpt Region:us Rmsnorm Rope Safetensors Scratch gpt Swiglu Welmia

Model Card on HF 🤗: https://huggingface.co/Welmia/welmia-2.0-103m-base

Welmia 2.0 103M Base Parameters and Internals

LLM Name	Welmia 2.0 103M Base
Repository 🤗	https://huggingface.co/Welmia/welmia-2.0-103m-base
Model Size	103m
Required VRAM	0.5 GB
Updated	2026-08-24
Maintainer	Welmia
Model Type	scratch_gpt
Model Files	0.5 GB
Supported Languages	en
Model Architecture	GPTForCausalLM
License	apache-2.0
Tokenizer Class	TokenizersBackend
Padding Token	<eos>
Vocabulary Size	24000
Torch Data Type	float32

Rank the Welmia 2.0 103M 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