Ollama 0.35 ships with Nimble support for fast local Mac inference
Technovangelist · x · 2026-09-30
Ollama 0.35 is out with support for Nimble, a model that reportedly runs fast locally on Mac while avoiding the security issues of the popular hosted version. The author shared a short demo video, with the full conversation linked.
Related event: Ollama 0.35 Adds Nimble Model Support for Fast Local Mac Inference(2 posts)→
More from Infra
- Jensen Huang on AI safety: contain agents, monitor them in real time with BlueField chip — XFreeze · 2026-09-30
- NVIDIA Vera CPU lands at Daytona office after running agentic workloads in testing — IanAndrewsDC · 2026-09-30
- Kafgres embeds a Rust Kafka broker inside Postgres, clients can't tell the difference — JiliJeanlouis · 2026-09-30
- Starlink Mobile goes live in Ecuador, bringing direct-to-cell coverage to the Amazon and Galápagos — elonmusk · 2026-09-30
- OpenRouter data: token usage exploding, some open-weight models see 10x spend since January — AccBalanced · 2026-09-30
- Reserve unlocked GPU capacity for startups, not just big logos — AccBalanced · 2026-09-30