What are the hardware requirements for PULI GPT 3SX?

PULI GPT 3SX requires approximately 13.8 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 PULI GPT 3SX and how large is it?

PULI GPT 3SX is developed by NYTK, a model with 6.9b 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 PULI GPT 3SX?

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

PULI GPT 3SX by NYTK — VRAM 13.8GB, 2K context

Name: PULI GPT 3SX
Author: NYTK

PULI GPT 3SX is an open-source language model by NYTK. Features: 6.9b LLM, VRAM: 13.8GB, Context: 2K, License: cc-by-nc-4.0, LLM Explorer Score: 0.05.

Endpoints compatible Gpt neox Hu Puli Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/NYTK/PULI-GPT-3SX

PULI GPT 3SX Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Limitations:

maximum sequence length of 2048

Additional Notes

Model is trained specifically for the Hungarian language.

Supported Languages

Hungarian (native)

Training Details

Data Sources:

Hungarian language sources

Data Volume:

36.3 billion words

Methodology:

Trained with EleutherAI's GPT-NeoX

Context Length:

2048

Model Architecture:

GPT-NeoX

Input Output

Input Format:

Token IDs

Accepted Modalities:

text

Output Format:

Generated text

LLM Name	PULI GPT 3SX
Repository 🤗	https://huggingface.co/NYTK/PULI-GPT-3SX
Model Size	6.9b
Required VRAM	13.8 GB
Updated	2026-08-04
Maintainer	NYTK
Model Type	gpt_neox
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 3.8 GB: 3-of-3 9.9 GB: 1-of-2 3.9 GB: 2-of-2
Supported Languages	hu
Model Architecture	GPTNeoXForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.37.0
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50048
Torch Data Type	float16
Errors	replace

Rank the PULI GPT 3SX 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

Quantized Models of the PULI GPT 3SX

Model	Likes	Downloads	VRAM
PULI GPT 3SX GPTQ	4	14	4 GB
PULI GPT 3SX GGML	5	7	3 GB

Best Alternatives to PULI GPT 3SX

Best Alternatives	Context / RAM	Downloads	Likes
Pythia 6.9B Deduped 8K	8K / 13.8 GB	11	1
Pythia 6.9B Deduped	2K / 13.8 GB	15102	7
Ppo Tldr 6.9B	2K / 13.8 GB	9	0
...I Pythia 6.9B Deduped Sft Tldr	2K / 27.4 GB	295	0
Pythia 6.9B	2K / 13.8 GB	50618	64
...I Pythia 6.9B Deduped Sft Tldr	2K / 13.8 GB	68	0
Oasst Pythia 6.9B 4000 Steps	2K / 13.8 GB	97	0
Pythia 6.9B HC3	2K / 27.7 GB	23	2
...an Large Pythia 6.9B Dev Phase	2K / 27.6 GB	6	3
Open Instruct Pythia 6.9B Tulu	2K / 27.6 GB	72	6

Note: green Score (e.g. "73.2") means that the model is better than NYTK/PULI-GPT-3SX.