LM Playground

Andriy Druk

About this app

LM Playground is designed as a universal platform for experimenting with various types of Large Language Models (LLMs) on your device. It allows users to download different LLMs, load them onto the application, and converse with these models. This setup allows for a hands-on exploration of the capabilities and distinctions between different LLMs, making it an invaluable tool for enthusiasts, researchers, or anyone curious about the advancements in language model technology.

Currently supported models:
• Meta Llama 3.2 1B and 3B
• Qwen 2.5 0.5B and 1.5B
• Google Gemma2 2B and 9B
• Microsoft Phi3.5
• Mistral 7B
• Llama 3.1 8B

This project was built based on llama.cpp project with OpenCL optimization for better performance. The application uses GGUF-format models with Q4KM quantization, which will be saved to the Downloads folder.

Ratings and reviews

Works great. Unfortunately, the larger Deepseek R1 gets stuck even after finishing the download and does not work at all. I downloaded it 3-4 times with same result. I think its due to a mismatch in model size. The downloaded file is 4.36GB and the file to be downloaded is 4.68GB.

I enjoy the experience with the LLMs, but the app itself could use more features and functions, with a UI upgrade. I love running Qwen models the most!

Great app. Works very well on the Poco F7 Ultra. Running 7b models. Saves all the faff of running ollama in a termux terminal.

What’s new

Added Copy, Upvote & Downvote buttons to every AI reply — tap Downvote to choose one or more feedback reasons in a panel and send.