Local coding stack: Qwen 3.6 35B-A3B delivers 5x speedup for free

5x for Free：本地编程栈

Tomasz Tunguz analyzed a 500+ comment Hacker News thread to map the local coding stack. Qwen 3.6 35B-A3B leads model mentions at 33%, with the 27B variant at 20%, followed by DeepSeek Pro and Gemma4 31B. All use MoE architectures that run on consumer hardware. For agents, Pi leads at 49% and OpenCode at 45%, both lightweight harnesses for local inference. One commenter compared local Qwen to a junior dev needing guidance versus Claude Opus as a senior who thinks with you on architecture—15x vs 5x speedup. But zero cost, full offline capability, and privacy make the tradeoff worthwhile for many. SWE-bench Verified scores back this up: Qwen3.6 27B hits 77.2%, the 35B-A3B MoE variant hits 73.4%, close to Claude Sonnet 4.6 at 79.6%.

Why it matters: Tunguz mined real local coding stack configs from 500+ HN comments: Qwen 3.6 35B-A3B at 33%, Pi at 49%, with MoE enabling consumer GPU inference. Concrete data with comparisons, not vendor fluff. Docked because it's secondhand curation rather than firsthand benchmarking, and t...