NO

Nous Capybara 34B iMat

NousGGUF by dranger003Updated 2024-02-18
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant13.7 GB
Quick answer

Nous Capybara 34B iMat needs about 16.2 GB of memory at IQ3_XXS (a 13.7 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 8.1 GB.

Nous Capybara 34B iMat is a 34.4B-parameter Nous model in GGUF format, quantized by dranger003. Its trained context length is 195K tokens. The repository has 1 quant file, from 13.7 GB (IQ3_XXS) to 13.7 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS13.7 GB 16.2 GB
Too big Get file →

What GPU do you need for Nous Capybara 34B iMat?

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 IQ3_XXS (13.7 GB file, about 16.2 GB in use).

Which Nous Capybara 34B iMat quant should you choose?

IQ3_XXS (13.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bydranger003
FamilyNous
Licensemit
Downloads (HF)27
Last updated2024-02-18

Frequently asked questions about Nous Capybara 34B iMat

How much VRAM does Nous Capybara 34B iMat need?

About 16.2 GB at IQ3_XXS with an 8K context window. That is the 13.7 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 Nous Capybara 34B iMat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nous Capybara 34B iMat GGUF?

It depends on the quant: IQ3_XXS is 13.7 GB.

What context length does Nous Capybara 34B iMat support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Nous Capybara 34B iMat GGUF?

The files are on Hugging Face in the dranger003/Nous-Capybara-34B-iMat.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 Nous Capybara 34B iMat use?

Hugging Face lists the license as mit. 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 dranger003

All by dranger003 →

More Nous models

All Nous →

Other large models

All large models →