Recommendations you can check.
AI research engineer working on LLMs; author of the Ahead of AI newsletter and of Build a Large Language Model (From Scratch).
7 things
OllamaSoftware Ollama
I am not affiliated with any of the tools mentioned in this article, but one nice thing about Ollama is that they also optionally support open-weight models hosted in the cloud
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
North Mini CodeSoftware Cohere
Alternatively, if you don't want to use Qwen3.6, Cohere's North Mini Code is probably the most interesting, capable alternative at this size class right now.
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
MLXSoftware Apple
I highly recommend using *-mlx versions of models working on Macs (if available).
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
CodexSoftware OpenAI
I have to admit that I still primarily alternate between Codex and Claude Code as my daily drivers, for now
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
Claude CodeSoftware Anthropic
I have to admit that I still primarily alternate between Codex and Claude Code as my daily drivers, for now
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
Qwen3.6Software
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
Qwen-CodeSoftware
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
Every entry is a verbatim quote and a link to the public post it came from. Nothing is paraphrased. If it is not on record somewhere public, it is not here.
The verdict is what they actually said: loved and liked are explicit; recommended means they told others to get it; uses means they only say they use it; read is a book on their public shelf with no verdict; mixed and disliked are kept too.
A dashed affiliate link, sponsored or their own label means the post disclosed a relationship. It is shown, never hidden.
The shading behind a date shows how dated a recommendation is for its kind of thing.
The shading behind a date shows how dated a recommendation is, for its kind of thing. Fully green is recent. It drains a quarter at a time as the post gets older, and is empty once it reads as dated.
What counts as old depends on the thing. A laptop praised four years ago has been replaced twice; a book loved twenty years ago is probably still loved. The shading is gone after about:
Stripes mean the post carries no date and the date shown is an estimate. No date at all, no shading.