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

Libraries

How to use unsloth/Kimi-K2-Instruct-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Kimi-K2-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/Kimi-K2-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Kimi-K2-Instruct-GGUF",
	filename="BF16/Kimi-K2-Instruct-BF16-00001-of-00045.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Kimi-K2-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/Kimi-K2-Instruct-GGUF with Ollama:
```
ollama run hf.co/unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Kimi-K2-Instruct-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 unsloth/Kimi-K2-Instruct-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 unsloth/Kimi-K2-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use unsloth/Kimi-K2-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

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": "unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Kimi-K2-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/Kimi-K2-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Kimi-K2-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Kimi-K2-Instruct-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Kimi-K2-Instruct-GGUF-UD-Q4_K_XL

List all available models

lemonade list

danielhanchen commited on Jul 14, 2025

Commit

1aab214

verified ·

1 Parent(s): fa9ce44

Upload folder using huggingface_hub

Browse files

Files changed (13) hide show

.gitattributes +12 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00001-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00002-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00003-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00004-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00005-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00006-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00007-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00008-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00009-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00010-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00011-of-00012.gguf +3 -0
IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00012-of-00012.gguf +3 -0

@@ -265,3 +265,15 @@ Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00013-of-00016.gguf filter=lfs diff=lfs merge=lfs
 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text

 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 Q5_K_M/Kimi-K2-Instruct-Q5_K_M-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00001-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00002-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00003-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00004-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00005-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00006-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00007-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00008-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00009-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00010-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00011-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/Kimi-K2-Instruct-IQ4_XS-00012-of-00012.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:42a45442bd540165379639d5d73ed182c11472610c4dacb426e0a55c89e69637
+size 47342205664

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d31e6e93a736ddca2753a8beae4664ca2acf4a0fe18b110d21c5b1650f3b22
+size 48386788768

+version https://git-lfs.github.com/spec/v1
+oid sha256:0cccf2102a21283f7e9181c48f17c1aa771c7508feb5da7926819c7851aec4bd
+size 48397827680

+version https://git-lfs.github.com/spec/v1
+oid sha256:49ead948ec559372d10c5872957b1e0852c18dc31376db50d29ea8b768f9cf05
+size 48445005376

+version https://git-lfs.github.com/spec/v1
+oid sha256:846e0f72d0a51babb7fdc3362fa3303b48affa379bfae1bc3e209030bfe46610
+size 48386788832

+version https://git-lfs.github.com/spec/v1
+oid sha256:af2c280cb82972a16e96ecf725049f0bed9a6618d09a9ceef123033b64efc23b
+size 15092954272

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

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

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

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