Runs Llama 70B on a single RTX 3090 (24GB VRAM) by streaming model layers through GPU memory via PCIe, with optional NVMe direct I/O that bypasses the CPU entirely. Achieves 83x speedup over mmap baseline for 70B on consumer hardware (RTX 3090 + 48 GB RAM). Q4_K_M fits 10 more layers in VRAM (36 vs 26), reducing tier B transfers. Don't run on multi-tenant/server systems Remove amd_iommu=off from /etc/default/grub , run update-grub , reboot 3 Patches NVIDIA DKMS ( os-mlock.c ) follow_pfn() was removed in kernel 6.12+. The NVMe disappears from /dev/ while bound to VFIO High if wrong device — never run on your boot drive.