Cactus ships 14MB Needle 2 for tool calling on cheap devices
Henry Ndubuaku and Roman Shemet designed Needle 2 to turn speech into typed actions on CPUs, with Pebble already running Needle locally.
By Ryan Merket · Published
Primary source: Cactus Compute
Why it matters
Needle 2 tests whether useful device agents can be specialized enough to run locally on cheap CPUs, cutting cloud costs without handing routine actions to a general-purpose model.
Cactus Compute founders Henry Ndubuaku (@Henry_Ndubuaku) and Roman Shemet (@RomanShemet) introduced Needle 2, a 14MB language model for tool calling on low-memory devices. The supplied product page does not display a separate launch date. Cactus Compute says the model can run on phones, wearables, home devices, robots and newer microcontrollers without a GPU or NPU.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.