Instructions to use Panchovix/Kimi-K2.6-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 Panchovix/Kimi-K2.6-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 Panchovix/Kimi-K2.6-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf Panchovix/Kimi-K2.6-GGUF:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Panchovix/Kimi-K2.6-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf Panchovix/Kimi-K2.6-GGUF:IQ3_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 Panchovix/Kimi-K2.6-GGUF:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf Panchovix/Kimi-K2.6-GGUF:IQ3_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 Panchovix/Kimi-K2.6-GGUF:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Panchovix/Kimi-K2.6-GGUF:IQ3_M

Use Docker

docker model run hf.co/Panchovix/Kimi-K2.6-GGUF:IQ3_M

LM Studio
Jan
Ollama
How to use Panchovix/Kimi-K2.6-GGUF with Ollama:
```
ollama run hf.co/Panchovix/Kimi-K2.6-GGUF:IQ3_M
```
Unsloth Desktop

How to use Panchovix/Kimi-K2.6-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Panchovix/Kimi-K2.6-GGUF:IQ3_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": "Panchovix/Kimi-K2.6-GGUF:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Panchovix/Kimi-K2.6-GGUF with Docker Model Runner:
```
docker model run hf.co/Panchovix/Kimi-K2.6-GGUF:IQ3_M
```

Lemonade

How to use Panchovix/Kimi-K2.6-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Panchovix/Kimi-K2.6-GGUF:IQ3_M

Run and chat with the model

lemonade run user.Kimi-K2.6-GGUF-IQ3_M

List all available models

lemonade list

Hermes Agent

How to use Panchovix/Kimi-K2.6-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 Panchovix/Kimi-K2.6-GGUF:IQ3_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 Panchovix/Kimi-K2.6-GGUF:IQ3_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Panchovix/Kimi-K2.6-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Panchovix/Kimi-K2.6-GGUF:IQ3_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 "Panchovix/Kimi-K2.6-GGUF:IQ3_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"

Model

This is a text-and-image-only GGUF quantization of moonshotai/Kimi-K2.6, made by @AesSedai. This means that video input is not present in this GGUF, and will not be available until support is added upstream in llama.cpp. MMPROJ files for image vision input have been provided.

This Q4_X quant is the "full quality" equivalent since the conditional experts are natively INT4 quantized directly from the original model, and the rest of the model is Q8_0.

The quants mentioned below are on https://huggingface.co/AesSedai/Kimi-K2.6-GGUF

Quant	Size	Mixture	PPL	1-(Mean PPL(Q)/PPL(base))	KLD
Q4_X	543.62 GiB (4.55 BPW)	Q8_0 / Q4_0	1.8248 +/- 0.00699	0	0
IQ3_S	377.50 GiB (3.16 BPW)	Q8_0 / varies	2.154629 ± 0.009004	+16.9764%	0.175223 ± 0.001218
IQ2_S	311.71 GiB (2.61 BPW)	Q8_0 / varies	2.492466 ± 0.011009	+35.3179%	0.321799 ± 0.001901
IQ2_XXS	262.74 GiB (2.20 BPW)	Q8_0 / varies	3.233051 ± 0.015424	+75.5248%	0.582627 ± 0.002755

Downloads last month: 47

GGUF

Model size

1T params

Architecture

deepseek2

Hardware compatibility

3-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Panchovix/Kimi-K2.6-GGUF

Base model

moonshotai/Kimi-K2.6

Quantized

(44)

this model