URGENTRUNTIME UPDATE·2026-06-12
ollama ships v0.30.8
▼ WHAT HAPPENED
ollama cut release v0.30.8 on 2026-06-12. Release notes excerpt: "## What's Changed * Fixed `ollama launch` selecting the wrong provider in some cases * Improved prompt caching by decoupling it from context shift for better KV cache reuse * More stable MLX inference with hardened linear and embedding layers * MLX runner now creates snapshots during prompt processing and speculative decoding for improved reliability * Impro..."
▼ OPERATOR ANGLE
Read the release notes and decide whether operators need to act. test throughput and memory fit before pinning the new version. Publish if this changes model compatibility, GPU backend behavior, memory use, quantization paths, security posture, migration requirements, or production serving reliability.
[pulse item] · runlocalai.co/pulse/gh-ollama-ollama-v0-30-8