Local Ai
v0.30.6-rc0
v0.30.6-rc0 is a release candidate that fixes kernel template instantiation so library symbols are exported correctly , following improvements from the v0.30 series. The v0.30 base release improved co
v0.30.6-rc0 is a release candidate that fixes kernel template instantiation so library symbols are exported correctly , following improvements from the v0.30 series. The v0.30 base release improved compatibility and performance using llama.cpp, augmented the MLX engine on Apple Silicon, and added support for a wider range of models including GGUF-based models and faster performance on NVIDIA hardware .
Source: Ollama Releases | 2026-06-05