What are the hardware requirements for Megatron Gpt2 345M?

Megatron Gpt2 345M requires approximately 0.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Megatron Gpt2 345M and how large is it?

Megatron Gpt2 345M is developed by robowaifudev, a model with 345m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Megatron Gpt2 345M perform on standard benchmarks?

Megatron Gpt2 345M has the following published scores: MMLU 24.32. Compare against reference models on this page or on the LLM Explorer leaderboards.

Megatron Gpt2 345M by robowaifudev — VRAM 0.7GB

Name: Megatron Gpt2 345M
Author: robowaifudev

Megatron Gpt2 345M is an open-source language model by robowaifudev. Features: 345m LLM, VRAM: 0.7GB, License: apache-2.0, LLM Explorer Score: 0.13, Arc: 24.2, HellaSwag: 39.2, MMLU: 24.3, GSM8K: 0.2.

Arxiv:1909.08053 Dataset:openwebtext Dataset:spacemanidol/cc-storie... Dataset:wikitext Deploy:azure En Endpoints compatible Gpt2 Model-index Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/robowaifudev/megatron-gpt2-345m

Megatron Gpt2 345M Parameters and Internals

Model Type

text generation

Additional Notes

This model is part of the Megatron-LM framework which supports model parallelism for training large models.

Training Details

Data Sources:

Wikipedia, RealNews, OpenWebText, CC-Stories

Methodology:

Generative left-to-right transformer similar to GPT-2

Model Architecture:

Transformer

Input Output

Input Format:

Text prompt

Accepted Modalities:

text

Output Format:

Generated text

LLM Name	Megatron Gpt2 345M
Repository 🤗	https://huggingface.co/robowaifudev/megatron-gpt2-345m
Model Size	345m
Required VRAM	0.7 GB
Updated	2026-07-18
Maintainer	robowaifudev
Model Type	gpt2
Model Files	0.7 GB 0.7 GB
Supported Languages	en
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Transformers Version	4.15.0
Vocabulary Size	50257
Activation Function	gelu_new

Rank the Megatron Gpt2 345M 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 Megatron Gpt2 345M

Best Alternatives	Context / RAM	Downloads	Likes
Anwgpt2 345M	0K / 1.4 GB	46	0
...ron Gpt2 345M Evol Instruct V2	0K / 1.4 GB	163	3
...gatron GPT 2 345M EvolInstruct	0K / 1.4 GB	174	4

Note: green Score (e.g. "73.2") means that the model is better than robowaifudev/megatron-gpt2-345m.