Open-weight composed language and speech model
Granite Switch 4.1
Granite Switch 4.1 is an IBM model family released on 14 October 2026 in 8B and 30B sizes under Apache 2.0. Each checkpoint bundles a Granite 4.1 base model, a Decision and a Guardian activated LoRA adapter and the Granite Speech 5.0 TurboCTC encoder, so one endpoint can serve chat, classification decisions and English speech-to-text.
Last reviewed 28 Oct 2026 · by IBM
Facts at a glance
| Developer | IBM |
|---|---|
| Released | 14 October 2026 source |
| Sizes | 8B and 30B base models plus a 470M speech encoder source |
| Context window | 131,072 tokens source |
| License | Apache 2.0 |
| Adapters | Decision aLoRA, Guardian Core aLoRA, Granite Speech 5.0 TurboCTC encoder source |
| Decision Index v0.3 (fast subset) | 8B: 42.9 overall; 30B: 50.1 overall source |
What Granite Switch 4.1 is used for
IBM built Granite Switch for applications that mix chat with fast yes-or-no or multiple-choice decisions, such as safety screening, routing or flagging, and with speech transcription. Adapters are activated by control tokens in the chat template and share the base model's KV cache, which IBM says keeps the composed model at roughly the same GPU memory as the base model alone. It runs in Hugging Face Transformers and in vLLM through a plug-in.
Questions people ask
- What is in a Granite Switch 4.1 checkpoint?
- A Granite 4.1 base model, a Decision aLoRA adapter, a Guardian Core aLoRA adapter for safety checks and the 470M-parameter Granite Speech 5.0 TurboCTC encoder for English speech-to-text.
- What license does Granite Switch 4.1 use?
- Apache 2.0, according to the model cards on Hugging Face.