KA

Kaiju 11B i

KaijuGGUF by SolidSnackeUpdated 2024-04-18
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant6.1 GB
Quick answer

Kaiju 11B i needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 6.1 GB (Q4_K_S) to 7.6 GB (Q5_K_M).

Kaiju 11B i is a 10.7B-parameter Kaiju model in GGUF format, quantized by SolidSnacke. Its trained context length is 4K tokens. The repository has 3 quant files, from 6.1 GB (Q4_K_S) to 7.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q5_K_M7.6 GB 8.9 GB
Too big Get file →

What GPU do you need for Kaiju 11B i?

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: the best quant that fits is Q5_K_M (7.6 GB file, about 9.7 GB in use).

Which Kaiju 11B i quant should you choose?

Q4_K_M is the usual starting point for Kaiju 11B i: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is Q4_K_S at 6.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bySolidSnacke
FamilyKaiju
Licensecc-by-4.0
Downloads (HF)66
Last updated2024-04-18

Frequently asked questions about Kaiju 11B i

How much VRAM does Kaiju 11B i need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Kaiju 11B i on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kaiju 11B i GGUF?

It depends on the quant: Q4_K_S is 6.1 GB, Q4_K_M is 6.5 GB, Q5_K_M is 7.6 GB.

What context length does Kaiju 11B i support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download Kaiju 11B i GGUF?

The files are on Hugging Face in the SolidSnacke/Kaiju-11B-i-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 Kaiju 11B i use?

Hugging Face lists the license as cc-by-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 SolidSnacke

All by SolidSnacke →

More Kaiju models

All Kaiju →

Other medium models

All medium models →