AnalysisAI ModelsAugust 8, 2026

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

Open the live feed