KI

Kimiko v3 1e

KimiGGUF by Chat-ErrorUpdated 2024-01-29
Download on Hugging Face
Parameters7.74B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

Kimiko v3 1e needs about 5.9 GB of memory at its main file (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.4 GB to 5.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kimiko v3 1e is a 7.74B-parameter Kimi model in GGUF format, quantized by Chat-Error. Its trained context length is 32K tokens. The repository has 3 quant files, from 4.4 GB to 5.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.4 GB 5.9 GB
Fits Get file →
—4.4 GB 5.9 GB
Fits Get file →
—5.5 GB 7.1 GB
Fits Get file →

What GPU do you need for Kimiko v3 1e?

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: the best quant that fits is the main file (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.5 GB file, about 7.1 GB in use).

Which Kimiko v3 1e quant should you choose?

If memory is tight, the smallest file is the first one in the table at 4.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.74B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byChat-Error
FamilyKimi
Licensemit
Downloads (HF)12
Last updated2024-01-29

Frequently asked questions about Kimiko v3 1e

How much VRAM does Kimiko v3 1e need?

About 5.9 GB at its main file with an 8K context window. That is the 4.4 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 Kimiko v3 1e on an 8 GB GPU?

Yes, with the smaller files: the 5.5 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kimiko v3 1e GGUF?

It depends on the quant: file is 4.4 GB, file is 4.4 GB, file is 5.5 GB.

What context length does Kimiko v3 1e support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Kimiko v3 1e GGUF?

The files are on Hugging Face in the Chat-Error/Kimiko-v3-1e repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Kimiko v3 1e 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 Chat-Error

All by Chat-Error →

More Kimi models

All Kimi →

Other small models

All small models →