The open‑source LLM runtime releases macOS, iOS and Linux builds, plus a chat API overhaul.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team published llama.cpp release b11531. It refactors the chat API and bundles pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu variants including CPU, Vulkan and CUDA 12.8. The download links are on the GitHub release page. Users can now run LLMs locally on more platforms without compiling themselves.
Developers can run Llama models locally on more devices today, avoiding build steps and supporting GPU acceleration on Ubuntu.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
