{"slug": "setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software", "title": "Setup advice for 5090, 4090 & 2080ti to get them all working for person software development", "summary": "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.", "body_md": "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.\n\nHardware:\n\n64GB 6000Mhz 9800X3D + RTX 5090\n\n32GB 3600Mhz 5900x + RTX 4090\n\n32GB 3200Mhz 3900 + RTX 2080ti\n\nRight 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).\n\nThe 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?\n\nMy 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.\n\nShould 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.", "url": "https://wpnews.pro/news/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software", "canonical_source": "https://forum.level1techs.com/t/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software-development/256617#post_1", "published_at": "2026-09-19 04:30:55+00:00", "updated_at": "2026-09-19 04:53:23.516692+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-tools", "ai-infrastructure"], "entities": ["RTX 5090", "RTX 4090", "RTX 2080ti", "Qwen 3.8 27B", "llama.cpp", "Godot", "Bazzite", "Deepseek Harness"], "alternates": {"html": "https://wpnews.pro/news/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software", "markdown": "https://wpnews.pro/news/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software.md", "text": "https://wpnews.pro/news/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software.txt", "jsonld": "https://wpnews.pro/news/setup-advice-for-5090-4090-2080ti-to-get-them-all-working-for-person-software.jsonld"}}