What are the hardware requirements for Rei 24B KTO?

Rei 24B KTO requires approximately 47.3 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rei 24B KTO and how large is it?

Rei 24B KTO is developed by Delta-Vector, 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 Rei 24B KTO?

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

Rei 24B KTO by Delta-Vector — VRAM 47.3GB, 128K context

Name: Rei 24B KTO
Author: Delta-Vector

Rei 24B KTO is an open-source language model by Delta-Vector. Features: 24b LLM, VRAM: 47.3GB, Context: 128K, LLM Explorer Score: 0.19.

Axolotl Base model:delta-vector/rei-24... Base model:finetune:delta-vect... Conversational Creative-writing Endpoints compatible Finetuned Kto Mistral Prose Region:us Roleplaying Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Rei-24B-KTO

Rei 24B KTO Parameters and Internals

LLM Name	Rei 24B KTO
Repository 🤗	https://huggingface.co/Delta-Vector/Rei-24B-KTO
Base Model(s)	Rei 24B Base Delta-Vector/Rei-24B-Base
Model Size	24b
Required VRAM	47.3 GB
Updated	2026-08-02
Maintainer	Delta-Vector
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
Model Architecture	MistralForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.53.1
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Rei 24B KTO 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 Rei 24B KTO

Best Alternatives	Context / RAM	Downloads	Likes
...ral Nemo Instruct 24B Merge V1	1000K / 24.6 GB	9	0
...all 3.1 24B Instruct 2503 Text	128K / 47.3 GB	22	0
Morbid Miasma 24B	128K / 47.3 GB	33	9
MagiSeek Pro V1	128K / 47.3 GB	303	1
Slimaki Tavern 24B V1.3	128K / 47.3 GB	346	16
Zepar 24B V1	128K / 47.3 GB	36	3
Cydonia 24B V4.3	128K / 47.3 GB	3652	138
Transformed Journey 24B	128K / 47.3 GB	65	0
Magistry Painted Cydonia 24B	128K / 47.3 GB	60	2
Morax 24B V2	128K / 18.3 GB	57	2

Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Rei-24B-KTO.