ComfyUI Node
Block Swap (RAM Offload)
Streams the first N transformer blocks from system RAM to the GPU on demand so models larger than VRAM can run. LoRA patches are baked in once at load time.
Block Swap (RAM Offload)
- model
- MODEL
◄blocks_to_swap20►
◄pin_memorytrue►
Categoryadvanced/model
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| blocks_to_swap | INT | 200–80 | Number of transformer blocks kept in system RAM and streamed to the GPU per forward pass. Raise if you still hit OOM. Automatically raised further when the resident part would not fit in VRAM. |
| pin_memory | BOOLEAN | true | Page-lock the CPU copies for faster PCIe transfers. Costs the same amount of non-swappable system RAM. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | — |