---
title: "5x for Free : The Local Coding Stack"
description: "A 500+ comment HN discussion reveals the current state of local AI coding - Qwen 3.6 35B dominates model mentions while Pi leads agents."
categories: ["AI"]
keywords: ["local AI models","Qwen","Pi coding agent","llama.cpp","local inference","AI coding"]
date: 2026-06-16
lastmod: 2026-07-23
canonical_url: https://www.tomtunguz.com/local-coding-models/
author: "Tomasz Tunguz"
---


Today, a Hacker News thread asked a simple question : "Has anyone replaced Claude/GPT with a local model for daily coding?"[^1] 500+ comments later, a clear picture emerged of the local coding stack.

[^1]: https://news.ycombinator.com/item?id=48542100

{{< email_image src="irt8x1fkzf338o4gcgdq" alt="Qwen3.6 35B-A3B dominates model mentions in local coding setups" width="540" height="291" >}}

Qwen 3.6 35B-A3B dominates model mentions at 33%, followed by the 27B variant at 20%. DeepSeek Pro & Gemma4 31B round out the top four. The common thread : mixture-of-experts architectures that run fast on consumer hardware.[^2]

[^2]: MoE models are large models that only activate a small fraction of their total parameters. Qwen 3.6 35B-A3B has 35 billion total parameters but only 3 billion active at inference time, while the 27B variant runs all 27 billion parameters each time.

{{< email_image src="vcicvldh36yog2g7bgqn" alt="Pi and OpenCode lead local coding agents" width="540" height="291" >}}

On the agent side, Pi leads at 49% with OpenCode close behind at 45%. Both are lightweight harnesses designed for local inference.

The thread surfaced a fascinating tradeoff. One commenter captured it perfectly :

> Comparing agentic Qwen3.6 35b to Claude Opus is like a junior with knowledge across the board, that you really need to guide, versus a senior that thinks with you on architecture. If Opus gives a 15x speedup, local and fully offline Qwen gives a 5x speedup.

But for many, the tradeoff is worth it. Privacy, zero cost, & complete offline capability matter.

> Given that it's completely free, is still mind-boggling to me.

The local coding stack is maturing fast. Qwen 3.6 35B-A3B has become the de facto standard & Pi the leading harness.

{{< email_image src="wjfs5qfayzywngv1ecph" alt="Local models approach frontier performance on SWE-bench Verified" width="540" height="291" >}}

The benchmark data backs up the sentiment. Qwen3.6 27B scores 77.2% & the MoE variant, Qwen3.6 35B-A3B, hits 73.4%. These two local models are within spitting distance of Claude Sonnet 4.6 (79.6%).[^3]

[^3]: SWE-bench Verified scores from [llm-stats.com](https://llm-stats.com/benchmarks/swe-bench-verified) & [morphllm.com](https://www.morphllm.com/claude-benchmarks), June 2026.

This is the [minimill pattern](https://tomtunguz.com/using-local-ai-to-work-faster/) playing out in real time. It's not just for CRM updates & web research. The current generation of local models is good enough for reasonable coding tasks.