KI

Kimi K3

KimiGGUF by vcruz305Updated 2026-09-26
Download on Hugging Face
Parameters1420B
Context1024K
Layers93
Architecturekimi-k3
Smallest quant320.3 GB
Quick answer

Kimi K3 needs about 489.3 GB of memory at IQ1_S (a 320.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 320.3 GB (IQ1_S) to 330.2 GB (IQ1_S). Longer context needs more: at 32K tokens the KV cache alone adds about 674.0 GB.

Kimi K3 – 2.8T‑parameter multimodal LLM with 1‑million‑token context

Kimi K3 is a 2.8T‑parameter multimodal model built on Kimi Delta Attention and Attention Residuals. It supports text, images, and video, and offers a 1‑million‑token context window. The model is open‑weight and released under the Kimi K3 License.

Good at

  • Long‑horizon coding
  • Agentic knowledge work
  • Native multimodality

Limits

  • Requires large VRAM – 489.3 GB at 8k context
  • No vision support in some builds
  • License is other, not standard

Best for

  • Large‑scale research
  • Long‑term coding sessions
  • Multimodal content creation

Who it’s for. Researchers and developers needing a high‑capacity multimodal LLM for complex, long‑context tasks. The model is suitable for those who can provision the necessary hardware and comply with the Kimi K3 License.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S320.3 GB (9 parts) 489.3 GB
Too big Get file →
IQ1_S330.2 GB (9 parts) 499.2 GB
Too big Get file →

For 8k context, the IQ1_S quant files are 320.33 GB and 330.17 GB. The estimated VRAM usage is 489.3 GB and 499.2 GB respectively. These sizes are approximate and require a GPU with several hundred gigabytes of memory. The dense‑path variant is the 320.33 GB file; do not mix shards.

What GPU do you need for Kimi K3?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Kimi K3 quant should you choose?

IQ1_S (320.3 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekimi-k3
Parameters1420B (approximate, mixture of experts)
Layers93
Trained context1,048,576 tokens
KV cache (fp16)20088 KB per token

Source

Quantized byvcruz305
FamilyKimi
Licenseother
Downloads (HF)580
Last updated2026-09-26

Frequently asked questions about Kimi K3

How much VRAM does Kimi K3 need?

About 489.3 GB at IQ1_S with an 8K context window. That is the 320.3 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 K3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 489.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kimi K3 GGUF?

It depends on the quant: IQ1_S is 320.3 GB, IQ1_S is 330.2 GB.

What context length does Kimi K3 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 168.5 GB at 8K and 674.0 GB at 32K.

Where can I download Kimi K3 GGUF?

The files are on Hugging Face in the vcruz305/Kimi-K3-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 Kimi K3 use?

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

Can I run Kimi K3 on 8 GB VRAM?

No. The IQ1_S quant requires about 489.3 GB of VRAM at 8k context, far beyond 8 GB.

What VRAM is needed for 16 GB?

Even 16 GB VRAM is insufficient; the model needs several hundred gigabytes of VRAM.

What license applies to Kimi K3?

The model is released under the Kimi K3 License, which is listed as other in the metadata.

Other GGUFs of Kimi-K3

Similar models

Browse all →

More from vcruz305

All by vcruz305 →

More Kimi models

All Kimi →

Other large models

All large models →