KI

KIMI K3 DERISKED MXFP4

KimiGGUF by Blackfrost-ResearchUpdated 2026-08-24
Download on Hugging Face
Parameters2780B
Context1024K
Layers—
Architecturekimi-k3
Smallest quant1508.4 GB
Quick answer

KIMI K3 DERISKED MXFP4 needs about 1689.9 GB of memory at MXFP4 (a 1508.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

KIMI K3 DERISKED MXFP4 is a 2780B-parameter Kimi model in GGUF format, quantized by Blackfrost-Research. Its trained context length is 1024K tokens. The repository has 1 quant file, from 1508.4 GB (MXFP4) to 1508.4 GB (MXFP4).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP41508.4 GB (38 parts) 1689.9 GB
Too big Get file →

What GPU do you need for KIMI K3 DERISKED MXFP4?

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: 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 DERISKED MXFP4 quant should you choose?

MXFP4 (1508.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekimi-k3
Parameters2780B
Trained context1,048,576 tokens

Source

FamilyKimi
Licenseother
Downloads (HF)0
Last updated2026-08-24

Frequently asked questions about KIMI K3 DERISKED MXFP4

How much VRAM does KIMI K3 DERISKED MXFP4 need?

About 1689.9 GB at MXFP4 with an 8K context window. That is the 1508.4 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 DERISKED MXFP4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 1689.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of KIMI K3 DERISKED MXFP4 GGUF?

It depends on the quant: MXFP4 is 1508.4 GB.

What context length does KIMI K3 DERISKED MXFP4 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download KIMI K3 DERISKED MXFP4 GGUF?

The files are on Hugging Face in the Blackfrost-Research/KIMI-K3-DERISKED-MXFP4-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 DERISKED MXFP4 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.

Similar models

Browse all →

More from Blackfrost-Research

All by Blackfrost-Research →

More Kimi models

All Kimi →

Other large models

All large models →