{"type":"post","stable_id":"post:llamafile-0105-local-model-runtime-refresh","slug":"llamafile-0105-local-model-runtime-refresh","title":"Llamafile 0.10.5 Refreshes The Local Model Runtime Around New Model Shapes","description":"Mozilla AI released llamafile 0.10.5 with newer llama.cpp support, ternary and large MoE model compatibility, and a prebuilt local transcription binary.","retrieval_nugget":"The release shows the maintenance burden of a portable local-model runtime: upstream inference changes, unusual weight formats, multimodal loading, large-context MoE checkpoints, and speech tooling must move together.","published_at":"2026-08-05","updated_at":"2026-08-05","record_date":"2026-08-05","date_kind":"published_at","topics":["local-ai","inference","open-models","multimodal"],"entities":["Mozilla AI","llamafile","Ternary Bonsai","Poolside"],"source_urls":["https://blog.mozilla.ai/llamafile-v0-10-5","https://github.com/mozilla-ai/llamafile/releases/tag/0.10.5"],"source_format":"article","editorial_timing":{"lane":"urgent_half_hour","scheduled_at":"2026-08-06T10:30:00+03:00","real_news_delta":"fresh release, incident, or legal escalation"},"visual_decision":{"status":"not_applicable","reason":"this is a release bundle across compatibility, packaging, and transcription rather than one mechanism; a diagram would be decorative","reviewed_by":"codex"},"schema_version":"newruntime-agent-readable-v0.2","status":"published","visuals":[],"routes":{"html":"https://newruntime.com/posts/llamafile-0105-local-model-runtime-refresh/","markdown":"https://newruntime.com/posts/llamafile-0105-local-model-runtime-refresh.md","json":"https://newruntime.com/posts/llamafile-0105-local-model-runtime-refresh.json"}}