Skip to content
Tech News
← Back to articles

Ollama update adds Ripple Preview coding model and Qwen3 memory cuts

read original get Samsung T7 Shield Portable SSD → more articles
GoKawiil Brief

Ollama, the open-source platform for running large language models locally on macOS, Linux and Windows, has released an update adding support for a new 65B 'Ripple Preview' model aimed at agentic coding tasks. The release also cuts memory usage for Qwen3.8 Flash Next by about 27 GiB on Apple Silicon, improves Claude Code integration, and adds CUDA 13.5 support for Windows on ARM.

Why It Matters

GoKawiil's interpretation of the reporting above, not reported fact.

The update continues Ollama's push to let developers run increasingly capable models on consumer hardware without cloud dependency, which could lower costs and improve privacy for AI workloads. The memory reduction and coding-focused model suggest growing emphasis on making agentic AI tools practical on local machines rather than requiring server-grade infrastructure.

Key Takeaways
Worth a Look

Samsung T7 Shield Portable SSD — Running multiple local LLMs with Ollama means downloading hefty multi-gigabyte model files, and a fast rugged portable SSD like the Samsung T7 Shield gives you plenty of extra space without slowing down your system drive. Its quick transfer speeds make loading and swapping between models like Llama 4 or DeepSeek-R1 much smoother. It's a simple way to keep your local AI setup organized and portable across machines.”,

See Samsung T7 Shield Portable SSD on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

Source: techspot.com, 2026-11-10

Published there as: “Ollama makes it easy to run AI models locally for free”

Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.