llama.cpp and ggml reach v1.0.0 with stricter semantic versioning
The ggml-org team released v1.0.0 of both llama.cpp (libllama) and ggml (libggml) on 13 November 2026, and says major-version bumps will now mark API and ABI breaks.
Self-hosted
Self-hosted models, inference hardware, runtimes, memory requirements, benchmarks and tutorials.
The ggml-org team released v1.0.0 of both llama.cpp (libllama) and ggml (libggml) on 13 November 2026, and says major-version bumps will now mark API and ABI breaks.
13:38
Minisforum has announced the MS-S1 MAX-P495, a compact local AI machine built around AMD's Ryzen AI Max+ PRO 495, but has given no price or release date.
17:40
How much memory a model really needs: weights, quantisation, the KV cache and overhead, with every figure computed by a script you can run.
17:40
Why memory bandwidth, not headline TOPS, sets how fast a local model talks, and where each kind of processor earns its place.
4 articles