Instructions to use kawasumi/Tema_Q-R-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use kawasumi/Tema_Q-R-4B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="kawasumi/Tema_Q-R-4B-GGUF", filename="Tema_Q-R-4B-Q4_K_M.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 kawasumi/Tema_Q-R-4B-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf kawasumi/Tema_Q-R-4B-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 kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf kawasumi/Tema_Q-R-4B-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 kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf kawasumi/Tema_Q-R-4B-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 kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use kawasumi/Tema_Q-R-4B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kawasumi/Tema_Q-R-4B-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": "kawasumi/Tema_Q-R-4B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
- Ollama
How to use kawasumi/Tema_Q-R-4B-GGUF with Ollama:
ollama run hf.co/kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
- Unsloth Studio
How to use kawasumi/Tema_Q-R-4B-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 kawasumi/Tema_Q-R-4B-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 kawasumi/Tema_Q-R-4B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for kawasumi/Tema_Q-R-4B-GGUF to start chatting
- Docker Model Runner
How to use kawasumi/Tema_Q-R-4B-GGUF with Docker Model Runner:
docker model run hf.co/kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
- Lemonade
How to use kawasumi/Tema_Q-R-4B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Tema_Q-R-4B-GGUF-Q4_K_M
List all available models
lemonade list
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M# Run inference directly in the terminal:
llama-cli -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_MUse 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 kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_MBuild 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 kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_MUse Docker
docker model run hf.co/kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M๐ Tema_Q-R-4B
๐ฅ ใขใใซๆฆ่ฆ
Tema_Q-R-4B๏ผๅคฉ้ฆฌๆฑ๏ผ ใฏใGoogleใ้็บใใ้ซๆง่ฝใชใชใผใใณใขใใซ Gemma 3 4B ใๅบ็คใซใใใๆฅๆฌ่ชใ่ฑ่ชใไธญๅฝ่ชๅใใฎๆน่ฏ็ๅคง่ฆๆจก่จ่ชใขใใซ๏ผLLM๏ผใงใใ
้ๅธธใฎGemma 3ใงใฏๅ็ญใ้ฃใใใใญใณใใใซๅฏพใใฆใใใใ่ช็ฑใงๆ็จใชๅฟ็ญใ็ๆใงใใใใ่จญ่จใใใฆใใพใใใฏใชใจใคใใฃใใชๅท็ญใ่ค้ใชใใญใฐใฉใใณใฐใฟในใฏใใใฃใผใใช็ฅ่ญๆขๆฑใชใฉใใใใใๅ้ใงAIใฎๅฏ่ฝๆงใๆๅคง้ใซๅผใๅบใใใใฆใผใถใผใซๆ้ฉใงใใ
Tema_Q-R-4B is an improved Large Language Model (LLM) tailored for Japanese, English, and Chinese, built upon Gemma 3 4B, a high-performance open model developed by Google.
It is designed to generate more flexible and useful responses, even for prompts that the standard Gemma 3 might find challenging to answer. It is ideal for users who wish to maximize the potential of AI in all fields, including creative writing, complex programming tasks, and deep knowledge exploration.
| ้ ็ฎ | ่ฉณ็ดฐ |
|---|---|
| ใใผในใขใใซ | Google Gemma 3 4B |
| ใขใใซๅ | Tema_Q-R-4B |
| ๅฏพๅฟ่จ่ช | ๆฅๆฌ่ช (JA), ่ฑ่ช (EN), ไธญๅฝ่ช (ZH) |
| ใขใใซใตใคใบ | 4 Billion Parameters |
| ใฉใคใปใณใน | Gemma 3ใฎใฉใคใปใณในใซๆบๆ |
| ้็บ | KY, TY, HY, KK |
๐ก๏ธ ่ฒฌไปปใใAIๅฉ็จใจๅญฆ็ฟใใผใฟใฎๅฎๅ จๆง
โ ๏ธ ่ฒฌไปปใใๅฉ็จใฎๅพนๅบ
- ใฆใผใถใผใฎ่ฒฌไปป: ใขใใซใฎๅฉ็จ่ ใฏใ็ๆใใใใณใณใใณใใใ้ฉ็จใใใๆณๅพใ่ฆๅถใใใใณHugging Faceใฎๅฉ็จ่ฆ็ด/ใณใณใใณใใใชใทใผใซๆบๆ ใใใใจใๅ จ้ข็ใซไฟ่จผใใๅฟ ่ฆใใใใพใใ
- ็ฆๆญขไบ้ : ใใฎใขใใซใใใใใชใๅทฎๅฅใใใฉในใกใณใใๆดๅใ้ๆณ่ก็บใใใใณๆๅฎณใช็ฎ็ใฎใใใซๅฉ็จใใใใจใๅบใ็ฆใใพใใ
- Downloads last month
- 17
4-bit
16-bit
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M# Run inference directly in the terminal: llama-cli -hf kawasumi/Tema_Q-R-4B-GGUF:Q4_K_M