ModelsIBM makes one model endpoint switch between chat, decisions and speech
Granite Switch 4.1 composes a base model, on-demand adapters and a speech encoder; efficiency claims still need workload-level testing.
IBM
Official website: IBM
Model-building research and analysis covering IBM.
Models
InferenceTogether's IBM expansion puts the inference service behind the chips
Together AI's October update describes an IBM Cloud-NVIDIA collaboration; IBM's original agreement sets a Q1 2027 availability expectation, so capacity plans must remain distinct from a generally available service.