The open‑source llama.cpp library now ships pre‑built binaries for macOS, iOS and several Ubuntu configurations, released on Oct 8 2026.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team published llama.cpp version b11514 on Oct 8 2026. The release includes ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and multiple Ubuntu builds (CPU, Vulkan and CUDA 12.8). Download links are provided on the GitHub release page.
Developers can run llama.cpp immediately on common desktop and mobile systems without compiling the code themselves.
Models
Claude now offers Motion for animated explainer videos and Dashboards for auto‑updating data views, available to paid users.
Models
Arena AI publishes a benchmark that scores 27 language models on 90,000 real‑world tasks, highlighting strengths and safety gaps.
Models
Cloudflare’s new Clef models can classify text, JSON, images or video and return structured decisions, with a 9B version hitting sub‑40 ms latency.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
