What are the hardware requirements for Gaslight 24B V1.0?

Gaslight 24B V1.0 requires approximately 47.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gaslight 24B V1.0 and how large is it?

Gaslight 24B V1.0 is developed by ReadyArt, a model with 24b 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 Gaslight 24B V1.0?

Gaslight 24B V1.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gaslight 24B V1.0 by ReadyArt — VRAM 47.3GB, 32K context

Name: Gaslight 24B V1.0
Author: ReadyArt

Gaslight 24B V1.0 is an open-source language model by ReadyArt. Features: 24b LLM, VRAM: 47.3GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.17.

Base model:finetune:thedrummer... Base model:thedrummer/cydonia-... Conversational Dangerous En Erp Explicit Gaslighting Mistral Nsfw Region:us Roleplay Safetensors Sharded Tensorflow Unaligned

Model Card on HF 🤗: https://huggingface.co/ReadyArt/Gaslight-24B-v1.0

Gaslight 24B V1.0 Parameters and Internals

LLM Name	Gaslight 24B V1.0
Repository 🤗	https://huggingface.co/ReadyArt/Gaslight-24B-v1.0
Base Model(s)	TheDrummer/Cydonia-24B-v2.1 TheDrummer/Cydonia-24B-v2.1
Model Size	24b
Required VRAM	47.3 GB
Updated	2025-10-28
Maintainer	ReadyArt
Model Type	mistral
Model Files	4.8 GB: 1-of-10 4.8 GB: 2-of-10 4.8 GB: 3-of-10 4.9 GB: 4-of-10 4.8 GB: 5-of-10 4.8 GB: 6-of-10 4.9 GB: 7-of-10 4.8 GB: 8-of-10 4.8 GB: 9-of-10 3.9 GB: 10-of-10
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.3
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Gaslight 24B V1.0 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 Gaslight 24B V1.0

Best Alternatives	Context / RAM	Downloads	Likes
...ral Nemo Instruct 24B Merge V1	1000K / 24.6 GB	9	0
Ouroboros 24B V1.4	128K / 47.3 GB	248	5
...all 3.1 24B Instruct 2503 Text	128K / 47.3 GB	16	0
Morbid Miasma 24B	128K / 47.3 GB	366	16
Doppelganger Twist 24B	128K / 47.3 GB	339	0
Zepar 24B V1	128K / 47.3 GB	200	5
MagiSeek Pro V1	128K / 47.3 GB	303	1
Slimaki Tavern 24B V1.3	128K / 47.3 GB	346	16
Cydonia 24B V4.3	128K / 47.3 GB	3652	138
Transformed Journey 24B	128K / 47.3 GB	65	0

Note: green Score (e.g. "73.2") means that the model is better than ReadyArt/Gaslight-24B-v1.0.