“888 KiB Assistant” but the assistant itself is a multi terabyte rental-only model stored in some mysterious data center.

amelius 4 hours ago | parent | next [-]

I'm getting "serverless" flashbacks.

kristianpaul 2 hours ago | parent | prev | next [-]

My model is at home... just 16Gb still a lot but just FYI

It seems to support connecting to your own LLM on the same LAN

	▲	croes an hour ago \| parent \| next [-]
		The point is the agent is still the LLM. No LLM, no agent.
	▲	dheera an hour ago \| parent \| prev [-]
		I tried connecting OpenClaw to ollama with a V100 running qwen3.5:35b but it was really, really, really slow (despite ollama itself feeling fairly fast). These "claw" agents really multiply the tokens used by an obscenely huge factor for the same request.