What are the hardware requirements for Celestial Order 24B V2?

Celestial Order 24B V2 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 Celestial Order 24B V2 and how large is it?

Celestial Order 24B V2 is developed by Sorihon, 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 Celestial Order 24B V2?

Celestial Order 24B V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Celestial Order 24B V2 by Sorihon — VRAM 47.3GB, 128K context

Name: Celestial Order 24B V2
Author: Sorihon

Celestial Order 24B V2 is an open-source language model by Sorihon. Features: 24b LLM, VRAM: 47.3GB, Context: 128K, Merged, LLM Explorer Score: 0.27.

Merged Model Arxiv:2311.03099 Base model:darkartsforge/morbi... Base model:sorihon/celestial-o... Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sorihon/Celestial-Order-24B-V2

Celestial Order 24B V2 Parameters and Internals

LLM Name	Celestial Order 24B V2
Repository 🤗	https://huggingface.co/Sorihon/Celestial-Order-24B-V2
Base Model(s)	Sorihon/Celestial-Order-24B Morbid Miasma 24B Sorihon/Celestial-Order-24B DarkArtsForge/Morbid-Miasma-24B
Merged Model	Yes
Model Size	24b
Required VRAM	47.3 GB
Updated	2026-08-26
Maintainer	Sorihon
Model Type	mistral
Model Files	4.9 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 3.8 GB: 10-of-10
Model Architecture	MistralForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	5.12.1
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072

Rank the Celestial Order 24B V2 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 Celestial Order 24B V2

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	16	0
Ouroboros 24B V1.4	128K / 47.3 GB	255	5
Morbid Miasma 24B	128K / 47.3 GB	368	16
Doppelganger Twist 24B	128K / 47.3 GB	342	0
Zepar 24B V1	128K / 47.3 GB	201	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 Sorihon/Celestial-Order-24B-V2.