Granite Switch 4.1 brings chat, decisions and speech to one endpoint
🎧 Listen to this story
The Granite Switch project announced Granite-Switch-4.1-8B and -30B, equipped with a Decision adapter for general-purpose decisions, a Guardian aLoRA for safety tasks and Granite-Speech-5.0-Turbo-CTC for transcription. The team says the automatic speech recognition model is the fastest on the OpenASR Leaderboard and that Guardian outperforms Jev 1.13, Microsoft-Decision-1, GPT-Luna-Decisions and Clef-Flash on average in safety-related decision tasks.
The three components are combined with the base model and use approximately the same video memory as the base model would use alone, the project says. A Hugging Face Space demonstrates transcription, summarization, harmful-content screening and 15 other checks in real time through a single endpoint. The team also plans to release an SDK so the community can train and combine its own adapters.
Why it matters · editorial interpretation
Combining conversation, transcription and decision-making in one endpoint could simplify applications that currently depend on several components, while the project says memory use remains similar to that of the base model, reducing deployment complexity. The planned SDK could also make it easier for the community to create and combine its own adapters.