What are the hardware requirements for Aurora Nights 103B V1.0?

Aurora Nights 103B V1.0 requires approximately 206.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aurora Nights 103B V1.0 and how large is it?

Aurora Nights 103B V1.0 is developed by sophosympatheia, a model with 103b 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 Nights 103B V1.0?

Aurora Nights 103B V1.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aurora Nights 103B V1.0 by sophosympatheia — VRAM 206.6GB, 4K context

Name: Aurora Nights 103B V1.0
Author: sophosympatheia

Aurora Nights 103B V1.0 is an open-source language model by sophosympatheia. Features: 103b LLM, VRAM: 206.6GB, Context: 4K, License: llama2, LLM Explorer Score: 0.1.

Arxiv:2307.11760 En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sophosympatheia/Aurora-Nights-103B-v1.0

Aurora Nights 103B V1.0 Parameters and Internals

Model Type

Roleplaying, Storytelling

Use Cases

Areas:

Roleplaying, Creative Writing

Considerations:

You are responsible for whatever you do with it.

Additional Notes

This model responds to prompting and is tuned for creativity in roleplaying scenarios.

Supported Languages

en (Full Proficiency)

Training Details

Context Length:

6144

Model Architecture:

120 layers

Input Output

Input Format:

Example context and prompt templates provided for SillyTavern

Accepted Modalities:

text

Output Format:

Text-based responses for roleplaying and storytelling

Performance Tips:

- Recommended max context is 6144 tokens. - Use Quadratic Sampling with smoothing factor 0.2 - 0.5. - Experiment with Min-P values and repetition penalties for optimal results.

LLM Name	Aurora Nights 103B V1.0
Repository 🤗	https://huggingface.co/sophosympatheia/Aurora-Nights-103B-v1.0
Model Size	103b
Required VRAM	206.6 GB
Updated	2026-07-16
Maintainer	sophosympatheia
Model Type	llama
Model Files	9.6 GB: 1-of-21 9.9 GB: 2-of-21 10.0 GB: 3-of-21 9.7 GB: 4-of-21 9.8 GB: 5-of-21 9.8 GB: 6-of-21 10.0 GB: 7-of-21 10.0 GB: 8-of-21 9.8 GB: 9-of-21 9.8 GB: 10-of-21 9.8 GB: 11-of-21 9.8 GB: 12-of-21 9.9 GB: 13-of-21 9.7 GB: 14-of-21 10.0 GB: 15-of-21 10.0 GB: 16-of-21 9.8 GB: 17-of-21 9.6 GB: 18-of-21 10.0 GB: 19-of-21 9.8 GB: 20-of-21 9.8 GB: 21-of-21
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Aurora Nights 103B V1.0 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

Quantized Models of the Aurora Nights 103B V1.0

Model	Likes	Downloads	VRAM
Aurora Nights 103B V1.0 GGUF	12	236	43 GB
Aurora Nights 103B V1.0 GPTQ	3	8	52 GB
Aurora Nights 103B V1.0 AWQ	1	4	54 GB

Best Alternatives to Aurora Nights 103B V1.0

Best Alternatives	Context / RAM	Downloads	Likes
Dark Miqu 103B	31K / 206.4 GB	30	2
BigWeave V15 103B	31K / 206.6 GB	85	2
Midnight Miqu 103B V1.5	31K / 206.4 GB	33	28
Midnight Miqu 103B V1.0	31K / 206.4 GB	85	16
Midnight Rose 103B V2.0.3	4K / 206.6 GB	93	13
OmegaDolphin 103B V0.1	4K / 175.6 GB	6	1
KitchenSink 103b	4K / 178.6 GB	13	9
Midnight Rose 103B V1.0	4K / 206.6 GB	11	3
Rogue Rose 103B V0.2	4K / 206.5 GB	12	33
Lila 103B L2	4K / 206.2 GB	0	0

Note: green Score (e.g. "73.2") means that the model is better than sophosympatheia/Aurora-Nights-103B-v1.0.