Ollama v0.34.1 graduates MLX safetensors model creation and speeds up /api/tags tenfold
Ollama
Ollama v0.34.1 (Sep 14) makes MLX safetensors creation via `ollama create` non-experimental, improves MLX memory handling on Apple Silicon, and cuts cold /api/tags response from ~3.1 s to 294 ms on large model libraries. GGUF model creation now requires llama.cpp tooling for safetensor conversion, and typical_p is deprecated for new model creation. v0.34.2-rc0 (Sep 15) bumps llama.cpp.
Why it matters
MLX creation going stable makes Apple Silicon a first-class path for building and quantizing local models inside Ollama.
Importance: 2/5
Minor version with a meaningful quality-of-life change for Apple Silicon users
Sources
official
ollama/ollama releases: v0.34.1