What are the hardware requirements for Aurora SCE 12B V2?

Aurora SCE 12B V2 requires approximately 24.5 GB of VRAM and supports a context window of 1000K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aurora SCE 12B V2 and how large is it?

Aurora SCE 12B V2 is developed by yamatazen, a model with 12b 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 Aurora SCE 12B V2?

Aurora SCE 12B V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aurora SCE 12B V2 by yamatazen — VRAM 24.5GB, 1000K context

Name: Aurora SCE 12B V2
Author: yamatazen

Aurora SCE 12B V2 is an open-source language model by yamatazen. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, Instruction-Based, Merged, LLM Explorer Score: 0.17.

Merged Model Arxiv:2408.07990 Base model:cyberagent/mistral-... Base model:elizezen/himeyuri-v... Base model:inflatebot/mn-12b-m... Base model:nbeerbower/mistral-... Base model:nbeerbower/mistral-... Base model:neversleep/lumimaid... Base model:pocketdoc/dans-pers... Chatml Conversational En Endpoints compatible Instruct Ja Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/yamatazen/Aurora-SCE-12B-v2

Aurora SCE 12B V2 Parameters and Internals

LLM Name	Aurora SCE 12B V2
Repository 🤗	https://huggingface.co/yamatazen/Aurora-SCE-12B-v2
Base Model(s)	MN 12B Mag Mell R1 NeverSleep/Lumimaid-v0.2-12B Elizezen/Himeyuri-v0.1-12B PocketDoc/Dans-PersonalityEngine-V1.1.0-12b ...tral Nemo 12B Abliterated LORA ...al Nemo Japanese Instruct 2408 Mistral Nemo Gutenberg 12B V4 inflatebot/MN-12B-Mag-Mell-R1 NeverSleep/Lumimaid-v0.2-12B Elizezen/Himeyuri-v0.1-12B PocketDoc/Dans-PersonalityEngine-V1.1.0-12b nbeerbower/Mistral-Nemo-12B-abliterated-LORA cyberagent/Mistral-Nemo-Japanese-Instruct-2408 nbeerbower/mistral-nemo-gutenberg-12B-v4
Merged Model	Yes
Model Size	12b
Required VRAM	24.5 GB
Updated	2026-08-01
Maintainer	yamatazen
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 4.9 GB: 5-of-5
Supported Languages	en ja
Model Architecture	MistralForCausalLM
Context Length	1024000
Model Max Length	1024000
Transformers Version	4.48.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Aurora SCE 12B 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 Aurora SCE 12B V2

Best Alternatives	Context / RAM	Downloads	Likes
...r Nemo 12B Instruct R 21 09 24	1000K / 24.5 GB	396277	141
Qliphoth 12B V1.1	1000K / 24.5 GB	22	3
Qliphoth 12B V1	1000K / 24.5 GB	26	2
SauerkrautLM Nemo 12B Instruct	1000K / 24.5 GB	1473	22
Magnum V4 12B	1000K / 24.5 GB	1116	54
MN Slush	1000K / 24.5 GB	181	32
...g M Claude Opus High Reasoning	1000K / 24.5 GB	82	3
ChatWaifu V1.4	1000K / 24.5 GB	335	20
ChatWaifu 12B V2.0	1000K / 24.5 GB	175	22
Mistral Nemo Bophades 12B	1000K / 24.5 GB	18	9

Note: green Score (e.g. "73.2") means that the model is better than yamatazen/Aurora-SCE-12B-v2.