Google announced that Gemma 4 is available, providing improved efficiency, expanded multimodal capabilities, and longer context support.
AMD is proud to offer Day 0 support for the full Gemma 4 model family across its entire AI-enabled hardware portfolio, with solutions suited for each of the Gemma 4 variants. AMD Day 0 support spans:
· AMD Instinct GPUs for cloud and enterprise datacenters
· AMD Radeon GPUs for AI workstations
· AMD Ryzen AI processors for AI PC and on-device inference
Support includes integration with AI applications and open-source software projects, including vLLM, SGLang, llama.cpp, Ollama, LM Studio, and Lemonade.
Developers can deploy select Gemma 4 models via Lemonade Server, which supports AMD’s latest XDNA™ 2 NPU for efficient on-device AI inference. Models can be deployed directly through the Ryzen AI LLM stack or integrated via Lemonade Server, with expanded NPU support coming in an upcoming Ryzen AI release.
If you have an interesting Article / Report/case study to share, please get in touch with us at editors@roymediative.com roy@roymediative.com, 9811346846/9625243429
