What are the hardware requirements for GPT Neo 2.7B Horni?

GPT Neo 2.7B Horni requires approximately 6.6 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GPT Neo 2.7B Horni and how large is it?

GPT Neo 2.7B Horni is developed by LyaaaaaGames, a model with 2.7b 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 Neo 2.7B Horni?

GPT Neo 2.7B Horni is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GPT Neo 2.7B Horni by LyaaaaaGames — VRAM 6.6GB, 2K context

Name: GPT Neo 2.7B Horni
Author: LyaaaaaGames

GPT Neo 2.7B Horni is an open-source language model by LyaaaaaGames. Features: 2.7b LLM, VRAM: 6.6GB, Context: 2K, LLM Explorer Score: 0.07.

Endpoints compatible Gpt neo Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/LyaaaaaGames/GPT-Neo-2.7B-Horni

GPT Neo 2.7B Horni Parameters and Internals

Model Type

text generation

Additional Notes

The model is a variant or sharded version specifically optimized for certain applications in creative writing or role-playing games. Details on the sharding approach and further adaptations for the named purpose are not specified. It is hosted and managed on the Hugging Face platform by KoboldAI.

LLM Name	GPT Neo 2.7B Horni
Repository 🤗	https://huggingface.co/LyaaaaaGames/GPT-Neo-2.7B-Horni
Model Size	2.7b
Required VRAM	6.6 GB
Updated	2026-08-08
Maintainer	LyaaaaaGames
Model Type	gpt_neo
Model Files	0.0 GB: 1-of-34 0.3 GB: 2-of-34 0.2 GB: 3-of-34 0.2 GB: 4-of-34 0.2 GB: 5-of-34 0.2 GB: 6-of-34 0.2 GB: 7-of-34 0.2 GB: 8-of-34 0.2 GB: 9-of-34 0.2 GB: 10-of-34 0.2 GB: 11-of-34 0.2 GB: 12-of-34 0.2 GB: 13-of-34 0.2 GB: 14-of-34 0.2 GB: 15-of-34 0.2 GB: 16-of-34 0.2 GB: 17-of-34 0.2 GB: 18-of-34 0.2 GB: 19-of-34 0.2 GB: 20-of-34 0.2 GB: 21-of-34 0.2 GB: 22-of-34 0.2 GB: 23-of-34 0.2 GB: 24-of-34 0.2 GB: 25-of-34 0.2 GB: 26-of-34 0.2 GB: 27-of-34 0.2 GB: 28-of-34 0.2 GB: 29-of-34 0.2 GB: 30-of-34 0.2 GB: 31-of-34 0.2 GB: 32-of-34 0.2 GB: 33-of-34 0.1 GB: 34-of-34
Model Architecture	GPTNeoForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.27.4
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50257
Torch Data Type	float16
Activation Function	gelu_new
Errors	replace

Rank the GPT Neo 2.7B Horni 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 Neo 2.7B Horni

Best Alternatives	Context / RAM	Downloads	Likes
ChildModel 02	2K / 5.3 GB	8	0
GPT Neo 2.7B Lama	2K / 10.6 GB	5	0
PRIME2 Openai	2K / 6.6 GB	4	1
EleutherAI GPT Neo 2.7B 4bits	2K / 1.7 GB	9	0
GPT Neo 2.7B	2K / 10.7 GB	56842	503
Pygmalion 2.7B	2K / 5.4 GB	214	59
... Style Transfer Using Examples	2K / 5.4 GB	5	1
Pygmalion 2.7B	2K / 0 GB	3	1
GPT Neo 2.7B Shinen	2K / 6.6 GB	5	0
GPT Neo 2.7B Horni LN	2K / 6.6 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than LyaaaaaGames/GPT-Neo-2.7B-Horni.