Running 426GB MXFP4 DeepSeek on 192GB VRAM to power a 4-sub-agent code review
HankYeomans · x · 2026-10-11
HankYeomans shares a preliminary demo of a code review setup where one agent spawns 4 sub-agents, powered by a 426GB MXFP4 "Frankenstein" quantized DeepSeek v4.1 running on just 192GB VRAM. He says he paused everything for days to build it and will soon publish a full writeup of the approach.
Related event: Developer Runs 426GB Quantized DeepSeek on 192GB VRAM(2 posts)→
More from coding & agent
- Prime Agent orchestrates 2,000+ agent swarm to rewrite itself in Rust, 13x faster startup — GregCook2011 · 2026-10-11
- Dario Amodei predicted software engineering automatable in 12 months — tech leaders say it's coming true — matthew_d_green · 2026-10-11
- Regents Labs runs a daily AI paper digest with ChatGPT Pro, spotlighting Prime Intellect's agent stack — seanwbren · 2026-10-11
- Building an Agent Feedback Loop to Auto-Tune Game Difficulty via Headless Simulation — zimmer550king · 2026-10-11
- Python vs Go vs Rust for production agentic systems: a six-dimension practical evaluation — mostly_deterministic · 2026-10-11
- Agent Use Cases: a free site scanning the web daily for 1,000+ real AI agent use cases — Roger_M_Taylor · 2026-10-11