KI

Kimi K3.1 Pro

KimiGGUF by DevQuasarUpdated 2026-11-07
Download on Hugging Face
Parameters2780B
Context1024K
Layers93
Architecturekimi-k31
Smallest quant1009.3 GB
Quick answer

Kimi K3.1 Pro needs about 1169.0 GB of memory at Q2_K (a 1009.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 1009.3 GB (Q2_K) to 1508.9 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 636.6 GB.

Kimi K3.1 Pro is a 2780B-parameter Kimi model in GGUF format, quantized by DevQuasar. Its trained context length is 1024K tokens. The repository has 2 quant files, from 1009.3 GB (Q2_K) to 1508.9 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1009.3 GB (33 parts) 1169.0 GB
Too big Get file →
MXFP4_MOE1508.9 GB (33 parts) 1668.5 GB
Too big Get file →

What GPU do you need for Kimi K3.1 Pro?

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 K3.1 Pro quant should you choose?

Q2_K (1009.3 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-k31
Parameters2780B (approximate, mixture of experts)
Layers93
Trained context1,048,576 tokens
KV cache (fp16)18972 KB per token

Source

Quantized byDevQuasar
FamilyKimi
Licenseother
Downloads (HF)274
Last updated2026-11-07

Frequently asked questions about Kimi K3.1 Pro

How much VRAM does Kimi K3.1 Pro need?

About 1169.0 GB at Q2_K with an 8K context window. That is the 1009.3 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 K3.1 Pro on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 1169.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kimi K3.1 Pro GGUF?

It depends on the quant: Q2_K is 1009.3 GB, MXFP4_MOE is 1508.9 GB.

What context length does Kimi K3.1 Pro 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 159.1 GB at 8K and 636.6 GB at 32K.

Where can I download Kimi K3.1 Pro GGUF?

The files are on Hugging Face in the DevQuasar/moonshotai.Kimi-K3.1-Pro-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 K3.1 Pro 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-K3.1-Pro

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Kimi models

All Kimi →

Other large models

All large models →