Hacker News new | ask | show | jobs
user: dryarzeg
created: 2025-12-21
karma: 157

submissions:

"Optimal Cognitive Core"- specialized 1.7B model for grounded question answering
6 points | 0 comments
Step 3.7 Flash – 198B-A11B MoE vision-language model
5 points | 0 comments
Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM
41 points | 4 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments