Instructions to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF",
	filename="moonshotai_Kimi-K2-Instruct-0905-IQ1_M/moonshotai_Kimi-K2-Instruct-0905-IQ1_M-00001-of-00006.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/moonshotai_Kimi-K2-Instruct-0905-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": "bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

Ollama
How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with Ollama:
```
ollama run hf.co/bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-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 bartowski/moonshotai_Kimi-K2-Instruct-0905-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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF to start chatting

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

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": "bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_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 bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_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 "bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_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"

Docker Model Runner
How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/moonshotai_Kimi-K2-Instruct-0905-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.moonshotai_Kimi-K2-Instruct-0905-GGUF-Q4_K_M

List all available models

lemonade list

bartowski commited on Sep 7, 2025

Commit

600d081

verified ·

1 Parent(s): effe9aa

Upload folder using huggingface_hub

Browse files

Files changed (17) hide show

.gitattributes +16 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00001-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00002-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00003-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00004-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00005-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00006-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00007-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00008-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00009-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00010-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00011-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00012-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00013-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00014-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00015-of-00016.gguf +3 -0
moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00016-of-00016.gguf +3 -0

@@ -155,3 +155,19 @@ moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-0001
 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text

 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 moonshotai_Kimi-K2-Instruct-0905-Q4_0/moonshotai_Kimi-K2-Instruct-0905-Q4_0-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00001-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00002-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00003-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00004-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00005-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00006-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00007-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00008-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00009-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00010-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00011-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00012-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00013-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+moonshotai_Kimi-K2-Instruct-0905-IQ4_NL/moonshotai_Kimi-K2-Instruct-0905-IQ4_NL-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2a847de08c3a4c6b13fb2eb274175cbd9119af644ba2b9067ead029548e172
+size 37308940160

+version https://git-lfs.github.com/spec/v1
+oid sha256:db942caed11157230709539e850c42e1920b68fc97c7ada80145d1aa59b6b2d5
+size 38558624384

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1372720852cc132e383b5c574182049ae83935834b47c014d11e9baab32671c
+size 38520089248

+version https://git-lfs.github.com/spec/v1
+oid sha256:b47919e5f48781ba4dcc5258c89a39a836274963f26fbd52faccde547b8eccce
+size 38531099328

+version https://git-lfs.github.com/spec/v1
+oid sha256:d394437e5b5443fd261057a8e65e7009026cdd2e4700a8f29bc6e74b592bddf9
+size 38525594304

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ad560f550ed0f2add147809d583a5f9dbddf05d915dac735540808d1c10466
+size 38520089280

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e179dbaefe7706cdf4e8651412e511d36c411a88528eff32716cdadf0871808
+size 38569634496

+version https://git-lfs.github.com/spec/v1
+oid sha256:f26c2a6fcf737927e88c9a55e6c53cf2bf84048007eecc7230c48850a23492ef
+size 3186491648

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@