NA

Nautilus RP 18B

NautilusGGUF by dasChronos1Updated 2024-09-16
Download on Hugging Face
Parameters18.2B
Context1000K
Layers62
Architecturellama
Smallest quant15.0 GB
Quick answer

Nautilus RP 18B needs about 17.6 GB of memory at Q6_K (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

Nautilus RP 18B is a 18.2B-parameter Nautilus model in GGUF format, quantized by dasChronos1. Its trained context length is 1000K tokens. The repository has 1 quant file, from 15.0 GB (Q6_K) to 15.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K15.0 GB 17.6 GB
Too big Get file →

What GPU do you need for Nautilus RP 18B?

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: the best quant that fits is Q6_K (15.0 GB file, about 17.6 GB in use).

Which Nautilus RP 18B quant should you choose?

Q6_K (15.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.2B
Layers62
Trained context1,024,000 tokens
KV cache (fp16)248 KB per token

Source

Quantized bydasChronos1
FamilyNautilus
Downloads (HF)9
Last updated2024-09-16

Frequently asked questions about Nautilus RP 18B

How much VRAM does Nautilus RP 18B need?

About 17.6 GB at Q6_K with an 8K context window. That is the 15.0 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 Nautilus RP 18B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nautilus RP 18B GGUF?

It depends on the quant: Q6_K is 15.0 GB.

What context length does Nautilus RP 18B 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 2.1 GB at 8K and 8.3 GB at 32K.

Where can I download Nautilus RP 18B GGUF?

The files are on Hugging Face in the dasChronos1/Nautilus-RP-18B-Q6_K-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 Nautilus RP 18B use?

Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from dasChronos1

All by dasChronos1 →

More Nautilus models

All Nautilus →

Other medium models

All medium models →