- Libraries
- Transformers
How to use tensorblock/Puma-3B-GGUF with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="tensorblock/Puma-3B-GGUF") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/Puma-3B-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tensorblock/Puma-3B-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 tensorblock/Puma-3B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/Puma-3B-GGUF:Q2_K
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/Puma-3B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/Puma-3B-GGUF:Q2_K
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 tensorblock/Puma-3B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/Puma-3B-GGUF:Q2_K
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 tensorblock/Puma-3B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/Puma-3B-GGUF:Q2_K
Use Docker
docker model run hf.co/tensorblock/Puma-3B-GGUF:Q2_K
- LM Studio
- Jan
- vLLM
How to use tensorblock/Puma-3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/Puma-3B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "tensorblock/Puma-3B-GGUF",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Use Docker
docker model run hf.co/tensorblock/Puma-3B-GGUF:Q2_K
- SGLang
How to use tensorblock/Puma-3B-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 "tensorblock/Puma-3B-GGUF" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "tensorblock/Puma-3B-GGUF",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "tensorblock/Puma-3B-GGUF" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "tensorblock/Puma-3B-GGUF",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}' - Ollama
How to use tensorblock/Puma-3B-GGUF with Ollama:
ollama run hf.co/tensorblock/Puma-3B-GGUF:Q2_K
- Unsloth Desktop
- Docker Model Runner
How to use tensorblock/Puma-3B-GGUF with Docker Model Runner:
docker model run hf.co/tensorblock/Puma-3B-GGUF:Q2_K
- Lemonade
How to use tensorblock/Puma-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/Puma-3B-GGUF:Q2_K
Run and chat with the model
lemonade run user.Puma-3B-GGUF-Q2_K
List all available models
lemonade list
- Atomic Chat
