The open‑source Llama inference library releases version b12387 with a 32‑bit bug fix and binaries for macOS, iOS and various Ubuntu builds.
NoteBy OossaPublished by Oossa: 1 min read
ggml‑org released llama.cpp version b12387 on 2026‑11‑14. The update fixes a ctz64 bug on 32‑bit systems. It also provides pre‑built binaries for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu flavours including x64, arm64 and s390x, with optional Vulkan and zDNN support.
The fix lets developers running 32‑bit hardware use llama.cpp reliably, and the new binaries simplify setup on common desktop and server platforms.
Models
Gemini 4 Carbon beats GPT‑6.1 Sol on the MathArena test but costs about 15 times more per query.
Models
The model turns camera images and instructions into robot movements. Runway says it led a simulation benchmark, but its tests have not been independently checked.
Models
OpenAI's new ChatGPT Wallet lets its ‘dots’ agents purchase items for U.S. Pro subscribers using tokenized card data.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
