LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active
(news.ycombinator.com)
1.
2.
Google’s latest on-device AI model is custom-made for your laptop
(androidauthority.com)
3.
Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM
(news.ycombinator.com)
4.
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request
(news.ycombinator.com)