Libraries Transformers How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="kth8/gemma-3-270m-it-Email-Generator-GGUF")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kth8/gemma-3-270m-it-Email-Generator-GGUF", dtype="auto") llama-cpp-python How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with llama-cpp-python:
# !pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="kth8/gemma-3-270m-it-Email-Generator-GGUF",
filename="gemma-3-270m-it-Email-Generator-Q4_0.gguf",
)
llm.create_chat_completion(
messages = [
{
"role": "user",
"content": "What is the capital of France?"
}
]
) Notebooks Google Colab Kaggle Local Apps llama.cpp How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with llama.cpp:
Install from brew brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kth8/gemma-3-270m-it-Email-Generator-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 kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kth8/gemma-3-270m-it-Email-Generator-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 kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kth8/gemma-3-270m-it-Email-Generator-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 kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M Use Docker docker model run hf.co/kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M LM Studio Jan vLLM How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with vLLM:
Install from pip and serve model # Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kth8/gemma-3-270m-it-Email-Generator-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": "kth8/gemma-3-270m-it-Email-Generator-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}' Use Docker docker model run hf.co/kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M SGLang How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with SGLang:
Install from pip and serve model # Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "kth8/gemma-3-270m-it-Email-Generator-GGUF" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "kth8/gemma-3-270m-it-Email-Generator-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}' Use Docker images docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "kth8/gemma-3-270m-it-Email-Generator-GGUF" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "kth8/gemma-3-270m-it-Email-Generator-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}' Ollama How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with Ollama:
ollama run hf.co/kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M Unsloth Studio new How to use kth8/gemma-3-270m-it-Email-Generator-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 kth8/gemma-3-270m-it-Email-Generator-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 kth8/gemma-3-270m-it-Email-Generator-GGUF to start chatting Using HuggingFace Spaces for Unsloth # No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kth8/gemma-3-270m-it-Email-Generator-GGUF to start chatting Docker Model Runner How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with Docker Model Runner:
docker model run hf.co/kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M Lemonade How to use kth8/gemma-3-270m-it-Email-Generator-GGUF with Lemonade:
Pull the model # Download Lemonade from https://lemonade-server.ai/
lemonade pull kth8/gemma-3-270m-it-Email-Generator-GGUF:Q4_K_M Run and chat with the model lemonade run user.gemma-3-270m-it-Email-Generator-GGUF-Q4_K_M List all available models lemonade list 
A fine-tune of unsloth/gemma-3-270m-it on the Kamisori-daijin/email-datasets-20k dataset.