Instructions to use ubergarm/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 ubergarm/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 ubergarm/Kimi-K2.6-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Kimi-K2.6-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Kimi-K2.6-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Kimi-K2.6-GGUF:Q2_K

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 ubergarm/Kimi-K2.6-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Kimi-K2.6-GGUF:Q2_K

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 ubergarm/Kimi-K2.6-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Kimi-K2.6-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Kimi-K2.6-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Kimi-K2.6-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Kimi-K2.6-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": "ubergarm/Kimi-K2.6-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Kimi-K2.6-GGUF:Q2_K

Ollama
How to use ubergarm/Kimi-K2.6-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Kimi-K2.6-GGUF:Q2_K
```

Unsloth Studio

How to use ubergarm/Kimi-K2.6-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ubergarm/Kimi-K2.6-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ubergarm/Kimi-K2.6-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Kimi-K2.6-GGUF to start chatting

How to use ubergarm/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 ubergarm/Kimi-K2.6-GGUF:Q2_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ubergarm/Kimi-K2.6-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ubergarm/Kimi-K2.6-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Kimi-K2.6-GGUF:Q2_K
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Kimi-K2.6-GGUF:Q2_K

Run and chat with the model

lemonade run user.Kimi-K2.6-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use ubergarm/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 ubergarm/Kimi-K2.6-GGUF:Q2_K

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 ubergarm/Kimi-K2.6-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ubergarm/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 ubergarm/Kimi-K2.6-GGUF:Q2_K

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 "ubergarm/Kimi-K2.6-GGUF:Q2_K" \
  --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"

How to use mmproj

by curiouspp8 - opened Apr 23

Discussion

curiouspp8

Apr 23

Is my understanding correct that if we pass mmproj into ik_llama model should be able to take images as an input? Perhaps opencode issue - tried that, then dropped an image there and ask what is this about and it said - can't read images. Any tips on that?

ubergarm

Owner Apr 23

Grab the mmproj from here (i suggest the bf16 as it is the "original" weights): https://huggingface.co/AesSedai/Kimi-K2.5-GGUF/tree/main
If you use -mmproj for right now I believe it will disable any --spec-type ... stuff
I'm not 100% sure, but you may want to set max-image-tokens to a value lower than the -ub
you can save VRAM by not offloading it with --no-mmproj-offload so it will run on CPU/RAM psure

Here is an example of what to add to your llama-server command assuming you're using -ub 4096 -b 4096

    --mmproj "$mmproj" \
    --image-min-tokens 1024 \
    --image-max-tokens 4096 \
   --no-mmproj-offload \

For opencode you have to configure it in your opencode.json to accept the inputs here is a snippet with the modalities shown:

    "cpu": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "cpu",
      "options": {
        "baseURL": "http://localhost:8088/v1",
        "timeout": 99999999999
      },
      "models": {
        "Kimi-K2.6": {
          "name": "Kimi-K2.6",
          "limit": {
            "context": 196608,
            "output": 131072
          },
          "cost": {
            "input": 5,
            "output": 25
          },
          "temperature": true,
          "reasoning": true,
          "tool_call": true,
          "modalities": {
            "input": ["text", "image"],
            "output": ["text"]
          }
        }
      }
    }

Beyond that, point your opencode at a git clone'd repo of ik_llama.cpp and ask it for more details then let me know how it works! haha

cheers and hope this gets you going!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment