Hugging Face releases Granite Switch 4.1 enabling chat, decision-making, and speech from one endpoint

Granite Switch 4.1 models, including Granite-Switch-4.1-8B and -30B, integrate a Decision aLoRA for general decision-making, a specialized Guardian aLoRA that outperforms Jev 1.13, Microsoft-Decision-1, GPT-Luna-Decisions, and Clef-Flash on safety tasks, and Granite-Speech-5.0-Turbo-CTC, the fastest ASR model on the OpenASR Leaderboard. All these capabilities run from a single hosted endpoint, using approximately the same VRAM as the base model alone, allowing for fast switching between chat, decision, and spoken requests.