Comfy-Org/comfy-aimdo

Memory Management for the GPU Poor, run the latest open source frontier models on consumer Nvidia GPUs

FlexTensor is a tensor offloading and management library for PyTorch that enables running large models on limited GPU memory by intelligently offloading tensors between GPU and CPU memory.

Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on different ports and loading/unloading them on demand

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.

ComfyUI-VRAM-Manager is an independent memory management custom node for ComfyUI. Provides Distorch memory management functionality for efficient GPU/CPU memory handling. Supports purging of SeedVR2, Qwen3-VL, and Nunchaku models (FLUX/Z-Image/Qwen-Image). Includes Model Patch Memory Cleaner.