Granite-Switch-4.1-8B / Granite-Switch-4.1-30B

Change history

15 Oct 2026

IBM combines transcription, decision-making and chat in a single Granite Switch model

Parameter	Before	Now
Capabilities per endpoint	Separate models/endpoints for chat, decisions, and speech	Chat, decision-making, and ASR transcription unified on one endpoint
VRAM usage	Not specified	Approximately same VRAM as base model alone, despite added capabilities
Decision adapters	No Decision aLoRA in prior release	General-purpose Decision aLoRA plus specialized Guardian aLoRA for safety decisions
ASR component	Not specified	Granite-Speech-5.0-Turbo-CTC embedded, top-ranked on OpenASR Leaderboard
Inference speed (decision throughput, 3B demo)	Competitor Jev reported at 10 decisions/second	Granite Switch 3B variant reached 60-100 decisions/second

News

Models· Important· 🧪 Worth Testing

IBM combines transcription, decision-making and chat in a single Granite Switch model

IBM has released Granite Switch 4.1 in 8B and 30B sizes, a modular system that runs chat, decision-making and speech transcription from one hosted endpoint instead of separate models. The update adds a general-purpose Decision adapter, a specialized Guardian adapter for safety-related classifications, and an embedded ASR model, Granite-Speech-5.0-Turbo-CTC, which tops the OpenASR Leaderboard. Despite bundling three capabilities, the combined model uses roughly the same VRAM as the base model alone.

2 hours agoHugging Face