GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

bullerwins/Kimi-K3-GGUF overview

Experimental version using https://github.com/ggml org/llama.cpp/pull/26185 For testing purposes "Full quality" as the original weights are mostly in mxfp4

ggufbase_model:moonshotai/Kimi-K3base_model:quantized:moonshotai/Kimi-K3endpoints_compatibleregion:us

Runs locally from ~209.32 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

4 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
mxfp4/Kimi-K3-mxfp4-00001-of-00004.ggufGGUFGGUF414.88 GBDownload
mxfp4/Kimi-K3-mxfp4-00002-of-00004.ggufGGUFGGUF414.87 GBDownload
mxfp4/Kimi-K3-mxfp4-00003-of-00004.ggufGGUFGGUF414.87 GBDownload
mxfp4/Kimi-K3-mxfp4-00004-of-00004.ggufGGUFGGUF209.32 GBDownload

Model Details

Model IDbullerwins/Kimi-K3-GGUF
Authorbullerwins
Pipeline
License
Base modelmoonshotai/Kimi-K3
Last modified2026-07-28T12:06:34.000Z

Model README

---

base_model:

  • moonshotai/Kimi-K3

---

Experimental version using https://github.com/ggml-org/llama.cpp/pull/26185

For testing purposes

"Full quality" as the original weights are mostly in mxfp4

Run bullerwins/Kimi-K3-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models