The open‑source LLM library llama.cpp now runs Kimi K3.1 vision on macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team released llama.cpp version b12259. It adds support for the Kimi K3.1 vision model and fixes preprocessing for K2.5 and K3.1. Pre‑built binaries are available for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds.
Developers can now run Kimi’s vision model locally on common desktop and mobile platforms without cloud services.
Models
The new world‑action model predicts future video and robot actions, letting robots pick up skills from a single human demonstration.
Models
ChatGPT will let users talk with brand‑verified agents for shopping help, starting with select US e‑commerce firms in beta.
Models
Claude Meetings, Whiteboards and Sheets launch in beta, with different paid-plan access. Anthropic also makes Claude Data generally available.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
