Qwen 35B-A3B MoE ~4x faster than 27B dense in local coding tests
On a R9700/llama.cpp setup, Qwen 35B-A3B MoE hit ~116 tok/s vs ~30 tok/s for Qwen 27B dense (~3.9x faster) on local coding-maintenance tasks, yet the quality gap was much smaller than expected; both handled ordinary bug fixes similarly.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills