What are the hardware requirements for PULI GPT 3SX GPTQ?

PULI GPT 3SX GPTQ requires approximately 4.2 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 GPTQ and how large is it?

PULI GPT 3SX GPTQ is developed by TheBloke, 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 GPTQ?

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

PULI GPT 3SX GPTQ by TheBloke — VRAM 4.2GB, 2K context

Name: PULI GPT 3SX GPTQ
Author: TheBloke

PULI GPT 3SX GPTQ is an open-source language model by TheBloke. Features: 6.9b LLM, VRAM: 4.2GB, Context: 2K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.08.

4-bit Base model:nytk/puli-gpt-3sx Base model:quantized:nytk/puli... Gpt neox Gptq Hu Puli Quantized Region:us Safetensors

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

PULI GPT 3SX GPTQ Parameters and Internals

Model Type

gptneox

Training Details

Data Volume:

36.3 billion words

Methodology:

Trained with EleutherAI's GPT-NeoX

Context Length:

2048

LLM Name	PULI GPT 3SX GPTQ
Repository 🤗	https://huggingface.co/TheBloke/PULI-GPT-3SX-GPTQ
Model Name	PULI GPT 3SX
Model Creator	NYTK
Base Model(s)	PULI GPT 3SX NYTK/PULI-GPT-3SX
Model Size	6.9b
Required VRAM	4.2 GB
Updated	2026-07-27
Maintainer	TheBloke
Model Type	gpt_neox
Model Files	4.2 GB
Supported Languages	hu
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	GPTNeoXForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.24.0
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 GPTQ 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 PULI GPT 3SX GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Cassandra 6.9B GPTQ	4K / 4.7 GB	6	2
...Int4 Step107000 GPTQ Wikitext2	2K / 4.2 GB	7	0
...Int3 Step107000 GPTQ Wikitext2	2K / 3.4 GB	6	0
... Int3 Step36000 GPTQ Wikitext2	2K / 3.4 GB	5	0
... Int3 Step71000 GPTQ Wikitext2	2K / 3.4 GB	5	0
...Int3 Step143000 GPTQ Wikitext2	2K / 3.4 GB	5	0
...Int3 Step110000 GPTQ Wikitext2	2K / 3.4 GB	5	0
...Int4 Step110000 GPTQ Wikitext2	2K / 4.2 GB	6	0
... Int4 Step71000 GPTQ Wikitext2	2K / 4.2 GB	5	0
...Int4 Step143000 GPTQ Wikitext2	2K / 4.2 GB	5	0

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