KI

moonshotai.Kimi K3

KimiGGUF by DevQuasarUpdated 2026-08-03
Download on Hugging Face
Parameters2780B
Context1024K
Layers93
Architecturekimi-k3
Smallest quant1008.9 GB
Quick answer

moonshotai.Kimi K3 needs about 1494.0 GB of memory at Q3_K_M (a 1325.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 1008.9 GB (Q2_K) to 1561.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 674.0 GB.

moonshotai.Kimi K3 is a 2780B-parameter Kimi model in GGUF format, quantized by DevQuasar. Its trained context length is 1024K tokens. The repository has 3 quant files, from 1008.9 GB (Q2_K) to 1561.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1008.9 GB (70 parts) 1178.0 GB
Too big Get file →
Q3_K_M1325.0 GB (93 parts) 1494.0 GB
Too big Get file →
BF161561.2 GB (100 parts) 1730.2 GB
Too big Get file →

What GPU do you need for moonshotai.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 moonshotai.Kimi K3 quant should you choose?

Q3_K_M (1325.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K at 1008.9 GB, with the quality trade-offs that come with fewer bits. 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
Parameters2780B (approximate, mixture of experts)
Layers93
Trained context1,048,576 tokens
KV cache (fp16)20088 KB per token

Source

Quantized byDevQuasar
FamilyKimi
Licenseother
Downloads (HF)193
Last updated2026-08-03

Frequently asked questions about moonshotai.Kimi K3

How much VRAM does moonshotai.Kimi K3 need?

About 1494.0 GB at Q3_K_M with an 8K context window. That is the 1325.0 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 moonshotai.Kimi K3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 1178.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of moonshotai.Kimi K3 GGUF?

It depends on the quant: Q2_K is 1008.9 GB, Q3_K_M is 1325.0 GB, BF16 is 1561.2 GB.

What context length does moonshotai.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 moonshotai.Kimi K3 GGUF?

The files are on Hugging Face in the DevQuasar/moonshotai.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 moonshotai.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.

Other GGUFs of Kimi-K3

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Kimi models

All Kimi →

Other large models

All large models →