Your cart is currently empty!
Run Llama, Mistral, Falcon, Claude, Phi, Mixtral, and other LLMs accelerated by the AMD Radeon PRO W7900 48gb GPU, on-device. Perfect for rapid development of large language models locally, or for running LLM applications serving responses to users quickly at the edge.
The AMD LLM Developer Kit is a small PC designed specifically for working with Large Language Models, either for local development and fine-tuning using GPU-accleration to speed up machine learning engineer tasks and workflows, or for use as an edge AI LLM inference server.
Weight | 10 lbs |
---|---|
Dimensions | 20 × 16 × 16 in |