The open‑source llama.cpp library (v b11556) now runs the 27‑billion‑parameter Prism Bonsai 2 model on macOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
ggml‑org released llama.cpp version b11556. The update adds runtime support for the Prism Bonsai 2 27B model. It also fixes Hadamard tensor handling and cleans up conversion code. Pre‑built binaries are provided for macOS (Apple Silicon and Intel) and Ubuntu (x64, arm64, s390x).
Developers can now run the large 27‑billion‑parameter Prism Bonsai 2 model locally on their own machines.
Models
Vals AI’s study shows multi‑agent setups can spend up to five times the tokens of a single model for only tiny quality gains.
Models
Odyssey’s Odyssey‑3 model can now generate and run 3‑D worlds from text prompts, with a free online demo and API sign‑ups.
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%.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
