# Local Open-Weight LLMs in Coding Harnesses

> Source: <https://sebastianraschka.com/blog/2026/local-open-weight-llms-coding-harnesses.html>
> Published: 2026-06-26 09:42:42+00:00

# Local Open-Weight LLMs in Coding Harnesses

I have been taking different local open-weight LLMs for a test drive in different harnesses (Qwen-Code, Codex, Claude Code).

30B Mixture-of-Experts models are kind of a nice sweet spot and can solve challenging problems. And they get roughly 40 tok/sec on a Mac or DGX Spark, which is similar to GPT 5.5 in a Pro subscription and totally usable for everyday work.

More interesting is also the harness choice! Claude Code seems to be using 2x as many tokens as Codex.

Gemma 4 E2B is here just for reference to show that the tasks can’t be trivially solved by smaller models.

The longer write-up is now available at [Using Local Coding Agents](https://magazine.sebastianraschka.com/p/using-local-coding-agents).

Source: lightly edited website version of my [Substack note](https://substack.com/@rasbt/note/c-283141629).

## Read Next

[Inkling: A New Open-Weight 975B MoE with a Few Surprises Short note on Thinking Machines Lab's 975B Inkling open-weight model, its benchmark profile, sparse MoE design, short convolutions, embedding RMSNorm, and](/blog/2026/inkling-architecture-benchmark-notes.html)

[200,000 Subscribers Short note celebrating Ahead of AI reaching 200,000 subscribers.](/blog/2026/ahead-of-ai-reached-200000-subscribers.html)

[GPT 5.6 Has 72 Possible Configurations. What's A Good Default? Short note on how GPT 5.6 model and effort choices map onto training-time and inference-time scaling, producing 72 configurations.](/blog/2026/gpt-5-6-configurations.html)