Guys forget about OMP or Codex, the best agent is actually a PSP from 2004
A whole 64MB of RAM at 333MHz , 480x272 display; it can't get any better than this running Qwen-3.8 27B through my GX10. completely unnecessary but it works beautifully
GPT-5.6 Sol Pro: 28:36 · 36.6K tokens · $0.72
0x Alpha Max: 52:25 · 86K tokens · FREE Qwen 3.8 Max: 15:43 · 29.5K tokens · $0.03 Grok 4.6 xhigh: 39:39 · 173K tokens ·
Qwen 3.8 27B
Deepseek Harness Time to complete: 12 minutes and 4 seconds Average tokens per second: 437 RTX5090 If Qwen 3.8 Next is better than 27B, wow.
Deleting my less-used local models to make way for Qwen 3.8 Flash
You have reached the end of the archive
All of qwen38