What are the hardware requirements for GTM 3 Base?

GTM 3 Base requires approximately 0.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GTM 3 Base and how large is it?

GTM 3 Base is developed by OPENGCM, a model with 105.6m 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 GTM 3 Base?

GTM 3 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GTM 3 Base by OPENGCM — VRAM 0.4GB

Name: GTM 3 Base
Author: OPENGCM

GTM 3 Base is an open-source language model by OPENGCM. Features: 105.6m LLM, VRAM: 0.4GB, License: apache-2.0, LLM Explorer Score: 0.34.

Base-model En From-scratch Gpt Gtm-gpt-rope Muon-optimizer Nanogpt Pytorch Region:us Research Rope Safetensors Single-gpu Slm Small-language-model

Model Card on HF 🤗: https://huggingface.co/OPENGCM/GTM-3-base

GTM 3 Base Parameters and Internals

LLM Name	GTM 3 Base
Repository 🤗	https://huggingface.co/OPENGCM/GTM-3-base
Model Size	105.6m
Required VRAM	0.4 GB
Updated	2026-09-17
Maintainer	OPENGCM
Model Type	gtm-gpt-rope
Model Files	0.4 GB
Supported Languages	en
License	apache-2.0
Is Biased	1
Vocabulary Size	50257

Rank the GTM 3 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