KI

kimi audio

KimiGGUF by vokraUpdated 2026-07-28
Download on Hugging Face
Parameters9.77B
Context—
Layers—
Architecture—
Smallest quant19.5 GB
Quick answer

kimi audio needs about 22.4 GB of memory at its main file (a 19.5 GB file) with an 8K context window, so it fits on a 24 GB GPU.

kimi audio is a 9.77B-parameter Kimi model in GGUF format, quantized by vokra. The repository has 1 quant file, from 19.5 GB to 19.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—19.5 GB 22.4 GB
Too big Get file →

What GPU do you need for kimi audio?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (19.5 GB file, about 22.4 GB in use).

Specifications

Architecture from the GGUF header

Parameters9.77B

Source

Quantized byvokra
FamilyKimi
Licensemit
Downloads (HF)20
Last updated2026-07-28

Frequently asked questions about kimi audio

How much VRAM does kimi audio need?

About 22.4 GB at its main file with an 8K context window. That is the 19.5 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 kimi audio on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of kimi audio GGUF?

It depends on the quant: file is 19.5 GB.

Where can I download kimi audio GGUF?

The files are on Hugging Face in the vokra/kimi-audio repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does kimi audio 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 vokra

All by vokra →

More Kimi models

All Kimi →

Other medium models

All medium models →