A local model generating faster than 20-30 tokens/sec is fast enough for practical local agent work, comparable to GPT 5.5's high-reasoning speed.

Raschka sets a practical speed bar of 20-30 tokens/sec for local coding agents, noting this matches GPT 5.5's "high" reasoning speed and that both Qwen3.6 and North Mini Code clear it easily. ✦ AI generated

Sebastian Raschka · Ahead of AI · 2026-06-27 · original ↗

Anyway, the bottom line is that, in my opinion, anything faster than 20-30 tok/sec is pretty reasonable for local agent work. This is about the same speed as GPT 5.5 with "high" reasoning. In this case, both models clear the bar easily.

Read full article ↗excerpt · fair-use quotation