Low VRAM mode
Low VRAM mode sends Ollama’s low_vram flag with every request, asking the daemon for smaller batches and a leaner KV cache. It trades throughput for the ability to run on hardware that would otherwise OOM.
Where to set it
There are two places this lives:
- Per chat — the Low VRAM toggle in the parameters panel. Affects just that conversation.
- Globally — Settings → Features → Low VRAM mode. Forces
low_vram: trueon every Ollama request.
Which one wins
The global setting overrides the per-chat toggle. When the global pin is on, the per-chat toggle shows up as pinned and disabled, with a pointer back to the setting so you understand why it cannot be flipped from the panel.
Turn the global setting off and you regain per-chat control.
Ollama only
The flag is meaningful only for the local Ollama backend. Loach does not send it to OpenAI-compatible endpoints — hosted services have no concept of your VRAM budget.