Instructions to use DKTechin/kanana with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use DKTechin/kanana 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 DKTechin/kanana:Q4_K_M # Run inference directly in the terminal: llama cli -hf DKTechin/kanana:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf DKTechin/kanana:Q4_K_M # Run inference directly in the terminal: llama cli -hf DKTechin/kanana: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 DKTechin/kanana:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf DKTechin/kanana: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 DKTechin/kanana:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf DKTechin/kanana:Q4_K_M
Use Docker
docker model run hf.co/DKTechin/kanana:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use DKTechin/kanana with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DKTechin/kanana" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DKTechin/kanana", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DKTechin/kanana:Q4_K_M
- Ollama
How to use DKTechin/kanana with Ollama:
ollama run hf.co/DKTechin/kanana:Q4_K_M
- Unsloth Studio
How to use DKTechin/kanana 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 DKTechin/kanana 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 DKTechin/kanana to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for DKTechin/kanana to start chatting
- Pi
How to use DKTechin/kanana with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DKTechin/kanana: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": "DKTechin/kanana:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use DKTechin/kanana with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DKTechin/kanana: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 "DKTechin/kanana: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 DKTechin/kanana with Docker Model Runner:
docker model run hf.co/DKTechin/kanana:Q4_K_M
- Lemonade
How to use DKTechin/kanana with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DKTechin/kanana:Q4_K_M
Run and chat with the model
lemonade run user.kanana-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use DKTechin/kanana with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf DKTechin/kanana: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 DKTechin/kanana:Q4_K_M
Run Hermes
hermes
- Atomic Chat
license: other
license_name: kanana
license_link: LICENSE
base_model: kakaocorp/kanana-2-3b-instruct
base_model_relation: quantized
pipeline_tag: text-generation
language:
- ko
- en
tags:
- gguf
- llama.cpp
- quantized
- kanana
Kanana 2 3B Instruct โ GGUF (Q4_K_M)
Powered by Kanana
kakaocorp/kanana-2-3b-instruct ๋ฅผ llama.cpp ์์ ๋ฐ๋ก ์ธ ์ ์๊ฒ GGUF ๋ก ๋ณํํ๊ณ 4bit(Q4_K_M) ์์ํํ ํ์ผ์
๋๋ค. ์๋ณธ ๋ฐฐํฌ์๋ GGUF ๊ฐ ์์ด ์ฌ๋ด ์จ๋๋ฐ์ด์ค(๋ก์ปฌ LLM) ์ฉ๋๋ก ์ง์ ๋ณํํ์ต๋๋ค.
| ํ์ผ | kanana-2-3b-instruct-Q4_K_M.gguf |
| ํฌ๊ธฐ | 2,161,793,408 bytes (2.01 GiB) |
| ์์ํ | Q4_K_M โ 4.92 BPW (์๋ณธ BF16 16.00 BPW) |
| ์ํคํ ์ฒ | qwen3 (์๋ณธ config.json ์ด Qwen3ForCausalLM) |
| ํ ํฌ๋์ด์ | tokenizer.ggml.pre = kanana2, vocab 128,256 |
| ์ปจํ ์คํธ | 32,768 (rope: yarn, factor 40, original 4,096) |
| ๋ํ ์์ | ์๋ณธ chat_template.jinja ๋ฅผ GGUF ๋ฉํ๋ฐ์ดํฐ์ ํฌํจ |
๋ณ๊ฒฝ ์ฌํญ (Kanana Open License ยง3.1(iii))
๊ฐ์ค์น์ ๊ฐ์ ๋ฐ๊พธ๋ ํ์ตยทํ์ธํ๋ยท๋ณํฉ์ ํ์ง ์์์ต๋๋ค. ์๋ณธ safetensors ๋ฅผ ์๋ ์ ์ฐจ๋ก ํ์ ๋ณํ + 4bit ์์ํ๋ง ํ์ต๋๋ค.
# llama.cpp @ 7e1e28c (2026-07-28)
python convert_hf_to_gguf.py kanana-2-3b-instruct --outtype bf16 \
--outfile kanana-2-3b-instruct-BF16.gguf
./build/bin/llama-quantize kanana-2-3b-instruct-BF16.gguf \
kanana-2-3b-instruct-Q4_K_M.gguf Q4_K_M
4bit ์์ํ๋ ์๋ณธ ๋๋น ํ์ง ์์ค์ ์๋ฐํฉ๋๋ค. ์๋ณธ ํ์ง์ด ํ์ํ๋ฉด ์ ๋งํฌ์ ์๋ณธ ์ ์ฅ์๋ฅผ ์ฐ์ธ์.
์ฌ์ฉ๋ฒ
# llama.cpp
llama-cli -hf DKTechin/kanana:Q4_K_M -c 2048 --jinja \
-sys "๋น์ ์ ์ฌ๋ด ๋ฉ์ ์ ๋ํ๋ฅผ ๊ฐ๊ฒฐํ๊ฒ ์์ฝํ๋ ๋์ฐ๋ฏธ์
๋๋ค." \
-p "์๋ ๋ํ๋ฅผ 3์ค๋ก ์์ฝํด์ค: ..."
LM StudioยทJanยทOllama ๋ฑ GGUF ๋ฅผ ์ฝ๋ ๋ฐํ์์์๋ ๊ทธ๋๋ก ์๋๋ค. ์์คํ ํ๋กฌํํธ ์์ด ์ฐ๋ฉด ์์ฝ ๋์ ์ ๋ ฅ์ ๋ํ์ดํ๋ ๊ฒฝํฅ์ด ์์ด, ์ญํ ์ ์ง์ ํ๋ ์์คํ ํ๋กฌํํธ๋ฅผ ํจ๊ป ์ฃผ๋ ํธ์ด ์์ ํฉ๋๋ค.
ํ์ธํ ๊ฒ ยท ํ์ธํ์ง ๋ชปํ ๊ฒ
- ํ์ธ: ๋ฉํ๋ฐ์ดํฐ(archยทtokenizer preยทropeยทchat template), ์ค์ ํ๊ตญ์ด ์์ฝ ์์ฑ, macOS/Metal ๊ธฐ์ค 2048 ํ ํฐ ์กฐ๊ฑด์์ ํ๋กฌํํธ 1,375 t/s ยท ์์ฑ 128 t/s.
- ๋ฏธํ์ธ: 32k ์ฅ๋ฌธ ํ์ง. ์๋ณธ
config.json์ rope ๋ฐฐ์๋ฅผ 40 ์ผ๋ก ์ ์ด ๋์์ง๋ง ๊ธธ์ด ๋น์จ(32,768 / 4,096)๋ก ๊ณ์ฐํ๋ฉด 8 ์ด๋ผ ์๋ก ๋ง์ง ์์ต๋๋ค. ์๋ณธ ํ์ด์ฌ ๋ฐํ์๊ณผ ๋์์ ๋ง์ถ๊ธฐ ์ํด ๋ช ์๊ฐ 40 ์ ๊ทธ๋๋ก ๊ธฐ๋กํ์ผ๋, ์์ฃผ ๊ธด ์ ๋ ฅ์์ ์ด์ํ๋ฉด ์ด ๊ฐ์ ๋จผ์ ์์ฌํ์ธ์.
๋ผ์ด์ ์ค
์ด ํ์ผ์ Kanana Open License Agreement ๋ฅผ ๋ฐ๋ฅด๋ ํ์๋ฌผ์
๋๋ค. ์ฌ๋ณธ์ ์ด ์ ์ฅ์์ LICENSE, ๊ณ ์ง ๋ฌธ๊ตฌ๋ NOTICE ์ ์์ต๋๋ค.
- ์ฌ์ฉ์๋ ์๋ณธ๊ณผ ๋์ผํ๊ฒ ๊ธ์ง๋ ์ฌ์ฉ ์ ์ฑ (Agreement ยง2.2) ๊ณผ KAKAO ์ Guidelines For Responsible AI ๋ฅผ ์ค์ํด์ผ ํ๋ฉฐ, ์ด ํ์ผ์ ์ฌ๋ฐฐํฌํ ๋์๋ ๊ฐ์ ์๋ฌด๋ฅผ ํ์ ์ฌ์ฉ์์๊ฒ ์๋ ค์ผ ํฉ๋๋ค.
- APIยทํด๋ผ์ฐ๋ ๋ฑ์ผ๋ก ์ 3์์๊ฒ ์ ๊ทผ์ ์ ๊ณตํ๊ฑฐ๋ ์ฌํ๋งคํ๋ ค๋ฉด KAKAO ์ ๋ณ๋ ์์ ๋ผ์ด์ ์ค๊ฐ ํ์ํฉ๋๋ค(Agreement ยง4).
- ์ด ํ์ผ์ ์ฌ์ฉํ๋ ์น์ฌ์ดํธยทUIยท๋ฌธ์์๋ "Powered by Kanana" ๋ฅผ ์์๋ณผ ์ ์๊ฒ ํ์ํด์ผ ํฉ๋๋ค(Agreement ยง3.1(v)).
Kanana is licensed in accordance with the Kanana Open License Agreement.
Copyright ยฉ KAKAO Corp. All Rights Reserved.