Instructions to use mmnga/K2-Think-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mmnga/K2-Think-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mmnga/K2-Think-gguf",
	filename="K2-Think-IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mmnga/K2-Think-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mmnga/K2-Think-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mmnga/K2-Think-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mmnga/K2-Think-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mmnga/K2-Think-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 mmnga/K2-Think-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mmnga/K2-Think-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 mmnga/K2-Think-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mmnga/K2-Think-gguf:Q4_K_M

Use Docker

docker model run hf.co/mmnga/K2-Think-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use mmnga/K2-Think-gguf with Ollama:
```
ollama run hf.co/mmnga/K2-Think-gguf:Q4_K_M
```

Unsloth Studio new

How to use mmnga/K2-Think-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 mmnga/K2-Think-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 mmnga/K2-Think-gguf to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use mmnga/K2-Think-gguf with Docker Model Runner:
```
docker model run hf.co/mmnga/K2-Think-gguf:Q4_K_M
```

Lemonade

How to use mmnga/K2-Think-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mmnga/K2-Think-gguf:Q4_K_M

Run and chat with the model

lemonade run user.K2-Think-gguf-Q4_K_M

List all available models

lemonade list

K2-Think-gguf

LLM360さんが公開しているK2-Thinkのggufフォーマット変換版です。

imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。

Usage

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
build/bin/llama-cli -m 'K2-Think-gguf' -n 128 -c 128 -p 'あなたはプロの料理人です。レシピを教えて' -cnv

Downloads last month: 40

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mmnga/K2-Think-gguf

Base model

Qwen/Qwen2.5-32B

Finetuned

LLM360/K2-Think

Quantized

(12)

this model

mmnga
/

K2-Think-gguf

K2-Think-gguf

Usage

Model tree for mmnga/K2-Think-gguf

Dataset used to train mmnga/K2-Think-gguf