MCP server: does a HF model fit your GPU/Mac/phone/cloud box, how fast, which quant, launch command. modelread.com
Patrick Devaney PRO
patrickbdevaney
AI & ML interests
Router-aware expert activation pruning, quantization, developing edge inference runtimes, fine-tuning, ai agent harnesses, open source ml research
Recent Activity
liked a model 1 day ago
Cactus-Compute/nemotron-3.5-120b-cq liked a model 1 day ago
HuggingFaceTB/SmolVLM2-256M-Video-Instruct liked a model 1 day ago
tencent/Hy4-flash