The main issue i found is that Qwen3.8-27B thinks a lot. On a hard problem the planner runs 32K tokens of reasoning and never writes the plan. Even with thinking off on Cerebras, a problem takes roughly 3 minutes and the 100 problems about 1.5 hours.
The main issue i found is that Qwen3.8-27B thinks a lot. On a hard problem the planner runs 32K tokens of reasoning and never writes the plan. Even with thinking off on Cerebras, a problem takes roughly 3 minutes and the 100 problems about 1.5 hours.