What are the hardware requirements for Aura NeMo 12B?

Aura NeMo 12B requires approximately 1.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aura NeMo 12B and how large is it?

Aura NeMo 12B is developed by jeiku, 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 Aura NeMo 12B?

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

Aura NeMo 12B by jeiku — VRAM 1.8GB

Name: Aura NeMo 12B
Author: jeiku

Aura NeMo 12B is an open-source language model by jeiku. Features: 12b LLM, VRAM: 1.8GB, Quantized, Instruction-Based, LLM Explorer Score: 0.14.

Arxiv:1910.09700 4bit Adapter Base model:adapter:unsloth/mis... Base model:unsloth/mistral-nem... Finetuned Instruct Lora Peft Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/jeiku/Aura-NeMo-12B

Aura NeMo 12B Parameters and Internals

LLM Name	Aura NeMo 12B
Repository 🤗	https://huggingface.co/jeiku/Aura-NeMo-12B
Base Model(s)	...al Nemo Instruct 2407 Bnb 4bit unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
Model Size	12b
Required VRAM	1.8 GB
Updated	2026-08-02
Maintainer	jeiku
Instruction-Based	Yes
Model Files	1.8 GB
Quantization Type	4bit
Model Architecture	Adapter
Model Max Length	1024000
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|gate_proj\|k_proj\|down_proj\|up_proj\|q_proj\|o_proj
LoRA Alpha	64
LoRA Dropout	0
R Param	128

Rank the Aura NeMo 12B 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 Aura NeMo 12B

Best Alternatives	Context / RAM	Downloads	Likes
Teleste Learner 12B	0K / 0.3 GB	250	1
Noodles 12B	0K / 3.6 GB	5	0
Control 12B R3 Lora	0K / 2.9 GB	6	0
Control 12B R3 Lora	0K / 2.9 GB	5	0
Aurora 12B	0K / 24.5 GB	12	0

Note: green Score (e.g. "73.2") means that the model is better than jeiku/Aura-NeMo-12B.