What are the hardware requirements for Llama 3 LewdPlay 8B Evo?

Llama 3 LewdPlay 8B Evo requires approximately 16 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3 LewdPlay 8B Evo and how large is it?

Llama 3 LewdPlay 8B Evo is developed by Undi95, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 LewdPlay 8B Evo perform on standard benchmarks?

Llama 3 LewdPlay 8B Evo has the following published scores: MMLU 67.87. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 LewdPlay 8B Evo by Undi95 — VRAM 16GB, 8K context

Name: Llama 3 LewdPlay 8B Evo
Author: Undi95

Llama 3 LewdPlay 8B Evo is an open-source language model by Undi95. Features: 8b LLM, VRAM: 16GB, Context: 8K, License: cc-by-nc-4.0, Merged, LLM Explorer Score: 0.13, Arc: 62.5, HellaSwag: 79.7, MMLU: 67.9, GSM8K: 68.5.

Merged Model Arxiv:2306.01708 Arxiv:2311.03099 Base model:undi95/llama-3-lewd... Base model:undi95/llama-3-unho... Base model:vicgalle/roleplay-l... Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Undi95/Llama-3-LewdPlay-8B-evo

Llama 3 LewdPlay 8B Evo Parameters and Internals

Additional Notes

This model is a merge of pre-trained language models using the EVOLVE merge method on MMLU. Unholy was used for uncensoring, Roleplay Llama 3 for the DPO train, and LewdPlay for lewd content.

Input Output

Input Format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {input}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {output}<|eot_id|>

LLM Name	Llama 3 LewdPlay 8B Evo
Repository 🤗	https://huggingface.co/Undi95/Llama-3-LewdPlay-8B-evo
Base Model(s)	Roleplay Llama 3 8B Llama 3 Unholy 8B E4 Llama 3 LewdPlay 8B vicgalle/Roleplay-Llama-3-8B Undi95/Llama-3-Unholy-8B-e4 Undi95/Llama-3-LewdPlay-8B
Merged Model	Yes
Model Size	8b
Required VRAM	16 GB
Updated	2026-08-06
Maintainer	Undi95
Model Type	llama
Model Files	9.9 GB: 1-of-2 6.1 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 LewdPlay 8B Evo 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 Llama 3 LewdPlay 8B Evo

Model	Likes	Downloads	VRAM
Llama 3 LewdPlay 8B Evo AWQ	0	5	5 GB

Best Alternatives to Llama 3 LewdPlay 8B Evo

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than Undi95/Llama-3-LewdPlay-8B-evo.