Instructions to use AtomicChat/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 AtomicChat/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 AtomicChat/Kimi-K3-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Kimi-K3-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

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 AtomicChat/Kimi-K3-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

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 AtomicChat/Kimi-K3-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

Use Docker

docker model run hf.co/AtomicChat/Kimi-K3-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use AtomicChat/Kimi-K3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Kimi-K3-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AtomicChat/Kimi-K3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Kimi-K3-GGUF:IQ1_M

Ollama
How to use AtomicChat/Kimi-K3-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Kimi-K3-GGUF:IQ1_M
```
Unsloth Desktop

How to use AtomicChat/Kimi-K3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AtomicChat/Kimi-K3-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/Kimi-K3-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Kimi-K3-GGUF:IQ1_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Kimi-K3-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Kimi-K3-GGUF-IQ1_M

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Kimi-K3-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AtomicChat/Kimi-K3-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AtomicChat/Kimi-K3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Kimi-K3-GGUF:IQ1_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "AtomicChat/Kimi-K3-GGUF:IQ1_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

worthant commited on Jul 31

Commit

c204d9f

verified ·

1 Parent(s): e6ea075

:ledger: docs(readme): Update quant quality metrics

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -103,11 +103,11 @@ Kimi K3 is a native vision language model, and as of this update the vision path
 | Quant     |    Size | PPL(Q)   | PPL(Q) / PPL(base)   | Mean KL div   | Top-1 match (%)| Δp RMS (%)      |
 |-----------|--------:|---------:|---------------------:|--------------:|---------------:|----------------:|
-| `IQ1_S`   |  590 GB | 2.524464 | 1.737654             | 0.539205      | 78.706 ± 0.363 | 35.446 ± 0.298  |
-| `IQ1_M`   |  690 GB | 2.171902 | 1.494977             | 0.395734      | 82.588 ± 0.336 | 30.284 ± 0.296  |
-| `IQ2_XXS` |  769 GB |          |                      |               |                |                 |
-| `Q3_K_S`  | 1197 GB |          |                      |               |                |                 |
-| `Q8_0`    | 2955 GB | 1.452800 | 1.00                 | 0             |         100    | 0               |
 **PPL(q)** - perplexity of the quant itself.
 **PPL / Q8_0** - the same number relative to

 | Quant     |    Size | PPL(Q)   | PPL(Q) / PPL(base)   | Mean KL div   | Top-1 match (%)| Δp RMS (%)      |
 |-----------|--------:|---------:|---------------------:|--------------:|---------------:|----------------:|
+| `IQ1_S`   |  590 GB | 2.5244   | 1.7376               | 0.5392        | 78.706         | 35.446          |
+| `IQ1_M`   |  690 GB | 2.1719   | 1.4949               | 0.3957        | 82.588         | 30.284          |
+| `IQ2_XXS` |  769 GB | 1.8794   | 1.2936               | 0.2594        | 87.231         | 23.883          |
+| `Q3_K_S`  | 1197 GB | 1.8541   | 1.2762               | 0.2384        | 87.694         | 22.617          |
+| `Q8_0`    | 2955 GB | 1.4528   | 1.00                 | 0             | 100            | 0               |
 **PPL(q)** - perplexity of the quant itself.
 **PPL / Q8_0** - the same number relative to