model-offloading

Quality-first local MiniMax H3 video-series generation and loopback API for dual RTX 4090 workstations, with native audio, references, P8/P9 continuity, and preserved artifacts.

Research preview for reproducible MoE routing and memory oversubscription on consumer GPUs. Not a production inference engine.

Deploying personal-grade production models on a consumer-grade PC

DualDeadline adds separate gate/up and down-projection transfer deadlines to exact MoE offloading, with H200 validation and Triton-optimized predictors.

Flash-backed mixture-of-experts inference on Apple devices with Swift/MLX.

A research toolbox for running and studying LLMs on constrained hardware, with memory, placement, inference, and benchmarking methods.

Local AI on Windows: Qwen 27B GGUF + Qwen-Image via llama.cpp and ComfyUI. 12GB VRAM / 16GB RAM, serial inference, automatic model switching, text-to-image and reference-image editing. 小显存本地大模型与生图工作流。

Stream PyTorch model blocks from NVMe or pinned CPU memory with a bounded GPU residency budget. LoRA-finetune models far larger than host RAM on one GPU - Qwen3-VL-32B and gpt-oss-120b train in under 6 GB of VRAM.

Research artifact for Memory-Sovereign Inference: Output-Exact Execution Beyond Full Residency