The open‑source llama.cpp library now supports several new low‑precision formats on WebGPU, and binaries for macOS, Linux and iOS are available.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team released llama.cpp version b11406. It adds WebGPU support for the MMVQ quantization paths Q1_0, Q5_0, Q5_1, Q3_K, Q5_K, Q6_K and MXFP4. The release also provides pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds (CPU, Vulkan and CUDA).
Developers can now run more memory‑efficient LLMs in browsers or on GPUs that use WebGPU, expanding where llama.cpp can be deployed.
Models
Canva's new AI creates up to 2K images with detailed layouts and editable text, available to all users via Dream Lab and the API.
Models
The update adds 14 voices, including Hindi and Finnish, and reaches existing generative-voice users without code changes or a price increase.
Models
Uber says its global workforce will use ChatGPT Work after an earlier 1,000-person pilot. The company has not disclosed the rollout’s cost.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
