Aurora Nights 103B v1.0 needs about 49.0 GB of memory at Q3_K_S (a 44.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 43.5 GB (Q2_K) to 49.5 GB (Q3_K_M).
Aurora Nights 103B v1.0 – a 103 billion‑parameter role‑playing LLM
Aurora Nights 103B v1.0 is a 103 billion‑parameter model built on the Aurora family with a 4096‑token context window. It excels at role‑playing and storytelling, following instructions well while maintaining creative writing and ERP abilities.
Good at
- Role‑playing and storytelling
- Instruction following
- Creative writing
Limits
- No vision support
- Requires large VRAM for full precision
- License is llama2
Best for
- Interactive fiction
- Character dialogue generation
- Narrative assistance
Who it’s for. Developers and writers who need a large, instruction‑aware model for immersive storytelling. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 43.5 GB | 46.0 GB | Too big | Get file → | |
| Q3_K_S | 44.5 GB | 47.0 GB | Too big | Get file → | |
| Q3_K_M | 49.5 GB | 52.0 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (43.51 GB file, ~48 GB memory at 8k context). For 12 GB VRAM use Q3_K_S (44.46 GB file, ~49 GB memory). For 16 GB VRAM use Q3_K_M (49.46 GB file, ~54 GB memory). Estimates are approximate.
What GPU do you need for Aurora Nights 103B v1.0?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q2_K (43.5 GB file, about 48.0 GB in use).
Which Aurora Nights 103B v1.0 quant should you choose?
Q3_K_S (44.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 43.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Aurora Nights 103B v1.0
How much VRAM does Aurora Nights 103B v1.0 need?
About 49.0 GB at Q3_K_S with an 8K context window. That is the 44.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Aurora Nights 103B v1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 48.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Aurora Nights 103B v1.0 GGUF?
It depends on the quant: Q2_K is 43.5 GB, Q3_K_S is 44.5 GB, Q3_K_M is 49.5 GB.
What context length does Aurora Nights 103B v1.0 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.
Where can I download Aurora Nights 103B v1.0 GGUF?
The files are on Hugging Face in the TheBloke/Aurora-Nights-103B-v1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Aurora Nights 103B v1.0 use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Aurora Nights 103B v1.0 on 8 GB VRAM?
Use the Q2_K quantized file; it requires about 48 GB of VRAM at 8k context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.