Instructions to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF",
	filename="Kimi-K2-Instruct-DRAFT-0.6B-128k-Q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-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 jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

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 jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

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 jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

Use Docker

docker model run hf.co/jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF with Ollama:
```
ollama run hf.co/jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
```

Unsloth Studio

How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-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 jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-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 jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF with Docker Model Runner:
```
docker model run hf.co/jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0
```

Lemonade

How to use jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jukofyork/Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF:Q4_0

Run and chat with the model

lemonade run user.Kimi-K2-Instruct-DRAFT-0.6B-v3.0-GGUF-Q4_0

List all available models

lemonade list

A 0.6B parameter draft (speculative decoding) model for use with Kimi-K2-Instruct.

See Kimi-K2-Instruct-DRAFT-0.6B-v3.0 for the models in transformers format, and a detailed explanation of how the model was created.

I've included the Q4_0 quants for 3 different context lengths:

NOTES:

The 14 heads of Qwen2.5-0.5B doesn't allow for any of the other 4-bit quants to be made (and experimentation has shown using more or less than 4-bits for speculative decoding is a waste of time anwyay).
Due to llama.cpp using "static-YaRN" the scaling factor remains constant regardless of input length! Only use the longer context versions when processing long contexts is required...
If you want to recreate these, then the TikToken / SentencePiece tokenizer mismatch requires a small hack to convert_hf_to_gguf.py (see main model page for details).