Lao Guo's Learning Space
Nov 17, 2026 · Artificial Intelligence
Loop-9B: 9B Model Matches 27B on Agent Tasks at Half Speed on 16GB Mac
SenseNova Loop-9B uses a looped transformer architecture to run 56 layer passes with only 9B parameters, achieving 27B-level performance on agent and coding tasks while fitting in 10GB VRAM, but generation speed is halved compared to standard 9B models.
Agent BenchmarksApple SiliconInference Speed Trade-off
0 likes · 16 min read
