Instructions to use bullerwins/Kimi-K3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bullerwins/Kimi-K3-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bullerwins/Kimi-K3-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf bullerwins/Kimi-K3-GGUF:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bullerwins/Kimi-K3-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf bullerwins/Kimi-K3-GGUF:MXFP4

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bullerwins/Kimi-K3-GGUF:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf bullerwins/Kimi-K3-GGUF:MXFP4

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bullerwins/Kimi-K3-GGUF:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bullerwins/Kimi-K3-GGUF:MXFP4

Use Docker

docker model run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4

LM Studio
Jan
Ollama
How to use bullerwins/Kimi-K3-GGUF with Ollama:
```
ollama run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4
```
Unsloth Desktop
Docker Model Runner
How to use bullerwins/Kimi-K3-GGUF with Docker Model Runner:
```
docker model run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4
```

Lemonade

How to use bullerwins/Kimi-K3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bullerwins/Kimi-K3-GGUF:MXFP4

Run and chat with the model

lemonade run user.Kimi-K3-GGUF-MXFP4

List all available models

lemonade list

Atomic Chat

Kimi-K3-GGUF / README.md

bullerwins

Update README.md

f9ee6c8 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

197 Bytes

metadata

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