MI

aurora 12b

MistralGGUF by XeroCodesUpdated 2024-07-30
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant13.0 GB
Quick answer

aurora 12b needs about 26.3 GB of memory at F16 (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 13.0 GB (Q8_0) to 49.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

aurora 12b is a 12.2B-parameter Mistral model in GGUF format, quantized by XeroCodes. Its trained context length is 1000K tokens. The repository has 3 quant files, from 13.0 GB (Q8_0) to 49.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_013.0 GB 14.9 GB
Too big Get file →
F1624.5 GB 26.3 GB
Too big Get file →
F3249.0 GB 50.8 GB
Too big Get file →

What GPU do you need for aurora 12b?

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: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).

Which aurora 12b quant should you choose?

F16 (24.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 13.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byXeroCodes
FamilyMistral
Licenseapache-2.0
Downloads (HF)41
Last updated2024-07-30

Frequently asked questions about aurora 12b

How much VRAM does aurora 12b need?

About 26.3 GB at F16 with an 8K context window. That is the 24.5 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 12b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of aurora 12b GGUF?

It depends on the quant: Q8_0 is 13.0 GB, F16 is 24.5 GB, F32 is 49.0 GB.

What context length does aurora 12b support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download aurora 12b GGUF?

The files are on Hugging Face in the XeroCodes/aurora-12b-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 12b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Mistral-Nemo-Instruct-2407

Similar models

Browse all →

More from XeroCodes

All by XeroCodes →

More Mistral models

All Mistral →

Other medium models

All medium models →