Instructions to use adityapanda2608112/PandaCoder-Pro-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use adityapanda2608112/PandaCoder-Pro-27B 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 adityapanda2608112/PandaCoder-Pro-27B
# Run inference directly in the terminal:
llama cli -hf adityapanda2608112/PandaCoder-Pro-27B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf adityapanda2608112/PandaCoder-Pro-27B
# Run inference directly in the terminal:
llama cli -hf adityapanda2608112/PandaCoder-Pro-27B

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 adityapanda2608112/PandaCoder-Pro-27B
# Run inference directly in the terminal:
./llama-cli -hf adityapanda2608112/PandaCoder-Pro-27B

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 adityapanda2608112/PandaCoder-Pro-27B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf adityapanda2608112/PandaCoder-Pro-27B

Use Docker

docker model run hf.co/adityapanda2608112/PandaCoder-Pro-27B

LM Studio
Jan

vLLM

How to use adityapanda2608112/PandaCoder-Pro-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adityapanda2608112/PandaCoder-Pro-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adityapanda2608112/PandaCoder-Pro-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adityapanda2608112/PandaCoder-Pro-27B

Ollama
How to use adityapanda2608112/PandaCoder-Pro-27B with Ollama:
```
ollama run hf.co/adityapanda2608112/PandaCoder-Pro-27B
```
Unsloth Desktop
Docker Model Runner
How to use adityapanda2608112/PandaCoder-Pro-27B with Docker Model Runner:
```
docker model run hf.co/adityapanda2608112/PandaCoder-Pro-27B
```

Lemonade

How to use adityapanda2608112/PandaCoder-Pro-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull adityapanda2608112/PandaCoder-Pro-27B

Run and chat with the model

lemonade run user.PandaCoder-Pro-27B-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

🐼 PandaCoder-Pro-27B

PandaCoder Pro 27B is an autonomous AI Software Engineering model created and developed by Aditya Panda at PandaLabs.

🌟 Overview:

PandaCoder Pro is engineered for autonomous reasoning, direct repository inspections, zero-shot full-stack code synthesis, automated bug debugging, and tool-augmented development.

⚙️ Technical Specifications:

Model Name: PandaCoder-Pro-27B
Author: Aditya Panda
Organization: PandaLabs
Parameters: 27.32 Billion
Format: GGUF
File Size: 16.24 GiB
Context Length: 16,384 tokens
License: Apache 2.0
Native Chat Template: Pre-baked system identity for Aditya Panda (PandaLabs)

🏢 Developed at:

PandaLabs by Aditya Panda.

Downloads last month: 33

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants