Ollama widens who can self-host: faster attention on older NVIDIA cards + integrated-GPU vision offload

Ollama's v0.31.2 release turns on flash attention for older NVIDIA GPUs (compute capability 6.x) and lets integrated GPUs run vision models by padding to fit memory — so more people can run current models on hardware they already own. It also hardens local model creation and makes the Claude Code launcher disable telemetry by default. The follow-on v0.32.0 release candidate adds support for the Qwen3.5/Next model family.

What it means The 'what can I run on my own box' frontier — broader hardware support lowers the bar for teams that want local, private inference instead of a hosted API.