What are the hardware requirements for Pygmalion 2 7B?

Pygmalion 2 7B requires approximately 13.5 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 7B and how large is it?

Pygmalion 2 7B is developed by PygmalionAI, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Pygmalion 2 7B perform on standard benchmarks?

Pygmalion 2 7B has the following published scores: MMLU 49.11. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pygmalion 2 7B by PygmalionAI — VRAM 13.5GB, 4K context

Name: Pygmalion 2 7B
Author: PygmalionAI

Pygmalion 2 7B is an open-source language model by PygmalionAI. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: llama2, Instruction-Based, HF Score: 51.1, LLM Explorer Score: 0.13, Arc: 54, HellaSwag: 78.2, MMLU: 49.1, TruthfulQA: 43.8, WinoGrande: 75.1, GSM8K: 6.4.

Dataset:databricks/databricks-... Dataset:jondurbin/airoboros-gp... Dataset:norquinal/claude multi... Dataset:open-orca/openorca Dataset:pygmalionai/pippa Deploy:azure En Instruct Llama Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/PygmalionAI/pygmalion-2-7b

Pygmalion 2 7B Benchmarks

ARC: 54.01 vs 96.7 (so35)^-44.1%

HellaSwag: 78.23 vs 95.3 (gpt4)^-17.9%

MMLU: 49.11 vs 88.3 (so35)^-44.4%

TruthfulQA: 43.78 vs 59 (gpt4)^-25.8%

WinoGrande: 75.14 vs 87.5 (gpt4)^-14.1%

GSM8K: 6.37 vs 96.4 (so35)^-93.4%

LLME Score: 0.13496

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Pygmalion 2 7B (PygmalionAI/pygmalion-2-7b)

🌟 Advertise your project 🚀

Pygmalion 2 7B Parameters and Internals

Model Type

text generation, instruct

Use Cases

Primary Use Cases:

Fictional writing, Conversation, Roleplaying, Story writing

Limitations:

Not fine-tuned to be safe and harmless. Output can be factually wrong, offensive, or socially unacceptable.

Considerations:

Intended for entertainment purposes, not for factual or safe outputs.

Additional Notes

Freely available for both commercial and non-commercial use

Supported Languages

en (advanced)

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 regular instruction data and roleplay data.

Input Output

Input Format:

<|system|>, <|user|>, <|model|> tokens for different roles.

Accepted Modalities:

text

Output Format:

Text output in response to input following the role scheme.

LLM Name	Pygmalion 2 7B
Repository 🤗	https://huggingface.co/PygmalionAI/pygmalion-2-7b
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-04-07
Maintainer	PygmalionAI
Model Type	llama
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2 10.0 GB: 1-of-2 3.5 GB: 2-of-2
Supported Languages	en
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

Quantized Models of the Pygmalion 2 7B

Model	Likes	Downloads	VRAM
Pygmalion 2 7B GGUF	34	2663	2 GB
Pygmalion 2 7B AWQ	5	9	3 GB
Pygmalion 2 7B GPTQ	15	29	3 GB

Best Alternatives to Pygmalion 2 7B

Best Alternatives	Context / RAM	Downloads	Likes
124	1024K / 16.1 GB	93	0
A5.4	1024K / 16.1 GB	12	0
A3.4	1024K / 16.1 GB	13	0
A2.4	1024K / 16.1 GB	12	0
... Qwen2.5llamaify 7B V23.1 200K	195K / 15.2 GB	24	5
SuperNeuralDreadDevil 8B	128K / 16.1 GB	23	1
Falcon3 7B Instruct	32K / 14.8 GB	18150	78
Falcon3 Jessi V0.4 7B Slerp	32K / 14.9 GB	9	9
Jessi V0.4 Falcon3 7B Instruct	32K / 14.8 GB	22	0
Jessi V0.5 Falcon3 7B Instruct	32K / 14.8 GB	10	0

Note: green Score (e.g. "73.2") means that the model is better than PygmalionAI/pygmalion-2-7b.

Rank the Pygmalion 2 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53570 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Pygmalion 2 7B by PygmalionAI