KI

Kimi-K3

KimiGGUF by hellohazimeUpdated 2026-08-18
Download on Hugging Face
Parameters1810B
Context1024K
Layers93
Architecturekimi-k3
Smallest quant441.4 GB
Quick answer

Kimi-K3 needs about 537.0 GB of memory at IQ1_S (a 441.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 441.4 GB (IQ1_S) to 478.5 GB (IQ2_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 380.3 GB.

Kimi-K3: 2.8T‑parameter multimodal model 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 available in two expert‑pruned GGUF builds for 512 GB memory.

Good at

  • Long‑horizon coding
  • Native multimodality
  • Large context window

Limits

  • No vision support listed in facts
  • License is other, not specified
  • No mention of GPU requirements

Best for

  • Research on multimodal AI
  • Large‑scale coding tasks
  • Long‑form content generation

Who it’s for. Researchers and developers needing a large multimodal model with extensive context. The model is open‑weight and can be run on a machine with 512 GB of memory using the provided GGUF builds.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S441.4 GB (10 parts) 537.0 GB
Too big Get file →
IQ2_XXS478.5 GB 574.1 GB
Too big Get file →

For 512 GB memory, use the IQ1_S build (file size 441.38 GB, estimated 537 GB at 8 k context) or the IQ2_XXS build (478.49 GB, 574.1 GB). Both are expert‑pruned and fully resident on a single 512 GB machine. The IQ1_S is slightly smaller, while IQ2_XXS offers higher precision.

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 (441.4 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
Parameters1810B
Layers93
Trained context1,048,576 tokens
KV cache (fp16)11334 KB per token

Source

Quantized byhellohazime
FamilyKimi
Licenseother
Downloads (HF)2,859
Last updated2026-08-18

Frequently asked questions about Kimi-K3

How much VRAM does Kimi-K3 need?

About 537.0 GB at IQ1_S with an 8K context window. That is the 441.4 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 Kimi-K3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 537.0 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 441.4 GB, IQ2_XXS is 478.5 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 95.1 GB at 8K and 380.3 GB at 32K.

Where can I download Kimi-K3 GGUF?

The files are on Hugging Face in the hellohazime/Kimi-K3-REAP-512GB-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 a machine with 512 GB of RAM?

Yes, the expert‑pruned builds are designed to fit fully resident on a 512 GB machine.

Does Kimi-K3 support vision?

The model is described as native multimodal, but the provided facts do not list vision support.

What is the context length of Kimi-K3?

The model supports a 1‑million‑token context window.

Other GGUFs of Kimi-K3-GGUF

Similar models

Browse all →

More from hellohazime

All by hellohazime →

More Kimi models

All Kimi →

Other large models

All large models →