5090 has 32GB VRAM.
It'd be silly to buy the 18k model to run a tiny model like Qwen 27B. You use models like GLM Flash and Qwen Next which won't fit on a single 5090.
can run multiple subagents of Qwen 27B though, right? Unless I am fundamentally misunderstanding how VRAM constraints work
Is it that silly? You could run multiple 27B models in parallel.
can run multiple subagents of Qwen 27B though, right? Unless I am fundamentally misunderstanding how VRAM constraints work