What are the hardware requirements for MS3.2 24B Stellar Skies?

MS3.2 24B Stellar Skies requires approximately 95.3 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 MS3.2 24B Stellar Skies and how large is it?

MS3.2 24B Stellar Skies is developed by Vortex5, 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 MS3.2 24B Stellar Skies?

MS3.2 24B Stellar Skies is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MS3.2 24B Stellar Skies by Vortex5 — VRAM 95.3GB, 128K context

Name: MS3.2 24B Stellar Skies
Author: Vortex5

MS3.2 24B Stellar Skies is an open-source language model by Vortex5. Features: 24b LLM, VRAM: 95.3GB, Context: 128K, Merged, LLM Explorer Score: 0.19.

Merged Model Base model:thedrummer/cydonia-... Base model:vortex5/ms3.2-24b-a... Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Vortex5/MS3.2-24B-Stellar-Skies

MS3.2 24B Stellar Skies Parameters and Internals

LLM Name	MS3.2 24B Stellar Skies
Repository 🤗	https://huggingface.co/Vortex5/MS3.2-24B-Stellar-Skies
Base Model(s)	Cydonia 24B V4 Vortex5/MS3.2-24B-Astral-Revenant TheDrummer/Cydonia-24B-v4 Vortex5/MS3.2-24B-Astral-Revenant
Merged Model	Yes
Model Size	24b
Required VRAM	95.3 GB
Updated	2026-07-15
Maintainer	Vortex5
Model Type	mistral
Model Files	2.7 GB: 1-of-22 4.9 GB: 2-of-22 4.5 GB: 3-of-22 4.5 GB: 4-of-22 4.5 GB: 5-of-22 4.5 GB: 6-of-22 4.5 GB: 7-of-22 4.5 GB: 8-of-22 4.5 GB: 9-of-22 4.5 GB: 10-of-22 4.5 GB: 11-of-22 4.5 GB: 12-of-22 4.5 GB: 13-of-22 4.5 GB: 14-of-22 4.5 GB: 15-of-22 4.5 GB: 16-of-22 4.5 GB: 17-of-22 4.5 GB: 18-of-22 4.5 GB: 19-of-22 4.5 GB: 20-of-22 4.5 GB: 21-of-22 2.2 GB: 22-of-22
Model Architecture	MistralForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.53.2
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the MS3.2 24B Stellar Skies 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 MS3.2 24B Stellar Skies

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
Celestial Order 24B V2	128K / 47.3 GB	127	3
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

Note: green Score (e.g. "73.2") means that the model is better than Vortex5/MS3.2-24B-Stellar-Skies.