Setup advice for 5090, 4090 & 2080ti to get them all working for person software development

A hobbyist software developer running three machines — a 9800X3D with an RTX 5090, a 5900X with an RTX 4090, and a 3900 with an unused RTX 2080ti — is asking for setup advice on running local LLMs across all three GPUs, currently running Qwen 3.8 27B nvfp4 at 200k context on the 5090 and a Q4_K_M model at 256k KV on the 4090. The developer's stated problem is a single-threaded workflow where only one GPU runs at a time, and he wants a multi-agent setup that uses both cards together while keeping him in control, and is also considering switching harnesses and repurposing the 2080ti as a small code-prediction model or dev box.

Need some tips/ideas on getting the most out of my gaming systems. Turns out the old “junkers” I didn’t want to sell have come back to be useful. I’m a software dev, but doing this as a hobbyist writing a game in Godot, more to learn about LLMs than to make a game. I learn best with a project. Hardware: 64GB 6000Mhz 9800X3D + RTX 5090 32GB 3600Mhz 5900x + RTX 4090 32GB 3200Mhz 3900 + RTX 2080ti Right now I’d call my configuration basic, running Qwen 3.8 27b nvfp4 for 5090 200k Context, full KV with MTPx4 & Vision, xhigh Bazzite + distro container for llama.cpp . I’m trying to move my gaming to Linux. It’s the workhorse. The 4090 Q4 K M 256k KV q 8 mid not sure its active though , also my Dev IDE: Godot, Deepseek Harness used to be OpenCode , VSCode and random python harnesses basic stuff like RAG and other AI type side projects . The 2080ti is unused. But feel I’m leaving compute on the table, wondering if there is anything productive it could be doing? Should I swap it to be my dev box, then use it as a small code predictor LLM. 4090 becoming dedicated LLM? My perceived issue is a single threaded methodology, one problem at a time either the 5090 is running or the 4090 is running not both. No idea how to go about getting a multi agent setup to have the both working well together, while still feeling like I’m in control. Maybe that is something I need to give up for better utilization. Should I switch up the harness? I’m convinced 50% of good AI output is down to a good harness. But not sure what would be better to unlock parallel tasking.