North Mini Code
Ranked 14 of 15 coding models by recommenders
Free model people say is competitive for everyday coding tasks, but critics say it makes more mistakes and struggles with tools.
Free model people say is competitive for everyday coding tasks, but critics say it makes more mistakes and struggles with tools.
6 people gave an opinion
- recommend it
- 6
- criticize it
- 0
- approval share
- 100%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong for its size
“better than anything you can run locally in ~8GB”
Comment from 1 Jul 2026 in “Qwen 3.6 27B is the sweet spot for local development” “felt this is good enough for 80-90% of my tasks”
Comment from 12 Jul 2026 in “Fable extended until 19 July”
What people warn about
Each mark is one comment
Makes a lot of mistakes
“You have MoE models (gemma 26b, qwen 35b, north mini code 30b) who are pretty fast, but make a lot of mistakes”
Comment from 16 Jun 2026 in “Running local models is good now” Weaker at finding security bugs
“it is a little worse than both for surfacing security bugs”
Comment from 1 Jul 2026 in “Qwen 3.6 27B is the sweet spot for local development” Struggles with tool use
“It just couldn't grasp the tools.”
Comment from 2 Oct 2026 in “Pi 1.0”
Other coding models people recommend
The four most recommended other coding models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Cursor Composer | 214 | 79 | 73% | 12 | 1 mo11 owners | Approved |
| Qwen3-Coder | 165 | 49 | 77% | 12 | 2 mo7 owners | Approved |
| GPT-5.3-Codex | 135 | 78 | 63% | 11 | 2 mo4 owners | — |
| Meta Muse Glimmer 30B | 70 | 18 | 80% | 3 | — | — |
| North Mini CodeThis page | 6 | 0 | 100% | 3 | — | — |
What people said
All 7 comments that mention it, newest first. Each links to the original comment.
“It just couldn't grasp the tools.”
“has honestly been very competitive in my personal assessment with many of the models coming out of the PRC”
“felt this is good enough for 80-90% of my tasks”
“it is a little worse than both for surfacing security bugs”
“better than anything you can run locally in ~8GB”
“it has not failed any tool calls I've asked it to make”
“You have MoE models (gemma 26b, qwen 35b, north mini code 30b) who are pretty fast, but make a lot of mistakes”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.