Model Releases
Another PR of ours just merged into llama.cpp: the fast Metal kernels from Monday now cover all 26 weight formats the Mac GPU runs. They mad…
Another PR of ours just merged into llama.cpp: the fast Metal kernels from Monday now cover all 26 weight formats the Mac GPU runs. They made speculative decoding faster on Mac for 10 formats, and thi
Another PR of ours just merged into llama.cpp: the fast Metal kernels from Monday now cover all 26 weight formats the Mac GPU runs. They made speculative decoding faster on Mac for 10 formats, and this PR adds the other 16, including BF16, MXFP4, Q2_K, Q3_K and the IQ quants. On an M3 Ultra, matrix multiplies run up to 4.4x faster when a model checks several tokens at once. Thanks @ggerganov for asking for it and merging it within a day. http://github.com/ggml-org/llama.cpp/pull/30065
Source: Georgi Gerganov (X) | 2026-10-07