sakamakismile/ThinkingCap-Qwen3.6-27B-NVFP4 Image-Text-to-Text • 17B • Updated 13 days ago • 3.8k • 20
NeutronStar Collection CUDA fork of antirez ds4 that runs giant MoE language models on a single consumer GPU by streaming routed experts from SSD. • 2 items • Updated 11 days ago