What are the hardware requirements for GPT 168?

GPT 168 requires approximately 0.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GPT 168 and how large is it?

GPT 168 is developed by gokulsrinivasagan, a model with 163m 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 GPT 168?

GPT 168 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GPT 168 by gokulsrinivasagan — VRAM 0.3GB

Name: GPT 168
Author: gokulsrinivasagan

GPT 168 is an open-source language model by gokulsrinivasagan. Features: 163m LLM, VRAM: 0.3GB, License: mit, LLM Explorer Score: 0.13.

Base model:finetune:gokulsrini... Base model:gokulsrinivasagan/g... Dataset:gokuls/wiki book corpu... Endpoints compatible Generated from trainer Gpt2 Model-index Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/gokulsrinivasagan/gpt_168

GPT 168 Parameters and Internals

LLM Name	GPT 168
Repository 🤗	https://huggingface.co/gokulsrinivasagan/gpt_168
Base Model(s)	gokulsrinivasagan/gpt_156 gokulsrinivasagan/gpt_156
Model Size	163m
Required VRAM	0.3 GB
Updated	2026-08-08
Maintainer	gokulsrinivasagan
Model Type	gpt2
Model Files	0.3 GB 0.0 GB
Model Architecture	GPT2LMHeadModel
License	mit
Model Max Length	1024
Transformers Version	4.42.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	50257
Torch Data Type	bfloat16
Activation Function	gelu_new

Rank the GPT 168 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 GPT 168

Best Alternatives	Context / RAM	Downloads
GPT 144	0K / 0.3 GB	7
GPT 132	0K / 0.3 GB	6
Gpt2 RMT 5	0K / 0.3 GB	31
Gpt2 RMT 3	0K / 0.3 GB	26
Gpt2 RMT 6	0K / 0.3 GB	25

Note: green Score (e.g. "73.2") means that the model is better than gokulsrinivasagan/gpt_168.