What are the hardware requirements for Pygmalion 2 13B GPTQ?

Pygmalion 2 13B GPTQ requires approximately 7.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pygmalion 2 13B GPTQ and how large is it?

Pygmalion 2 13B GPTQ is developed by TheBloke, a model with 13b 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 Pygmalion 2 13B GPTQ?

Pygmalion 2 13B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pygmalion 2 13B GPTQ by TheBloke — VRAM 7.3GB, 4K context

Name: Pygmalion 2 13B GPTQ
Author: TheBloke

Pygmalion 2 13B GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.3GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

4-bit Base model:pygmalionai/pygmali... Base model:quantized:pygmalion... Dataset:databricks/databricks-... Dataset:jondurbin/airoboros-gp... Dataset:norquinal/claude multi... Dataset:open-orca/openorca Dataset:pygmalionai/pippa En Gptq Instruct Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/Pygmalion-2-13B-GPTQ

Pygmalion 2 13B GPTQ Parameters and Internals

Model Type

text generation, instruct, conversation, roleplaying, storywriting

Use Cases

Areas:

Fictional writing, entertainment

Limitations:

Outputs may be factually wrong or misleading., Potential to produce socially unacceptable or undesirable text., May contain profanity and texts that are lewd or offensive.

Considerations:

Not fine-tuned to be safe and harmless.

Training Details

Data Sources:

PygmalionAI/PIPPA, Open-Orca/OpenOrca, Norquinal/claude_multiround_chat_30k, jondurbin/airoboros-gpt4-1.4.1, databricks/databricks-dolly-15k

Methodology:

Supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories, and conversations with synthetically generated instructions attached.

Model Architecture:

Based on Llama-2 13B

Input Output

Input Format:

LLM Name	Pygmalion 2 13B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/Pygmalion-2-13B-GPTQ
Model Name	Pygmalion 2 13B
Model Creator	PygmalionAI
Base Model(s)	Pygmalion 2 13B PygmalionAI/pygmalion-2-13b
Model Size	13b
Required VRAM	7.3 GB
Updated	2026-07-22
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	7.3 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Pygmalion 2 13B 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 Pygmalion 2 13B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven 13B GPTQ	16K / 7.3 GB	35	7
CodeLlama 13B Instruct GPTQ	16K / 7.3 GB	75	39
Leo Hessianai 13B Chat GPTQ	8K / 7.3 GB	47	1
...sianai 13B Chat Bilingual GPTQ	8K / 7.3 GB	2	4
...lama2 13B Orca V2 8K 3166 GPTQ	8K / 7.3 GB	48	24
Mythalion 13B GPTQ	4K / 7.3 GB	2005	52
Swallow 13B Instruct GPTQ	4K / 7.5 GB	6	2
...2 13B Ft Instruct Es Gptq 3bit	4K / 5.7 GB	6	3
LoKuS 13B GPTQ	4K / 7.3 GB	71	2
Speechless Llama2 13B GPTQ	4K / 7.3 GB	7	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Pygmalion-2-13B-GPTQ.