# Ministral

Hacker Approved page: https://hackerapproved.com/p/ministral/

14 people recommended Ministral in Hacker News comments, 3 had mixed feelings and 5 criticized it, November 2025 to October 2026. It was recommended in 7 of 12 months, in 14 threads. It meets the Hacker Approved badge rule.

**Verdict:** Small free models people run locally for fast data extraction and simple tasks; critics say they trail larger models and are weak at vision.

Summary written by Claude from 28 comments. It was written before the November 2026 recount, and 26 of those comments still count.

## Why people recommend it

- Fast responses for small tasks (4 comments in the sample): "It's faster than other models of similar size I used previously, fast enough that I never wait for it" ([source](https://news.ycombinator.com/item?id=47195535)) "I was pleasantly surprised by how fast and accurate these small models have become" ([source](https://news.ycombinator.com/item?id=46932018)) "its actually much faster than Google/DDG searches and I use it a ton when coding" ([source](https://news.ycombinator.com/item?id=48174686))
- Runs locally on modest hardware (3 comments in the sample): "still running Qwen and Ministral and their like on local hardware" ([source](https://news.ycombinator.com/item?id=46838215)) "I run Ministral-3b on my hardware as my go-to" ([source](https://news.ycombinator.com/item?id=48237809)) "Works fine on gaming PCs." ([source](https://news.ycombinator.com/item?id=46470988))
- Accurate and consistent results (2 comments in the sample): "I have processed several hundred receipts this way with very high accuracy" ([source](https://news.ycombinator.com/item?id=46346871)) "it performed the best in my benchmarks" ([source](https://news.ycombinator.com/item?id=47406517))
- Useful for receipts and data extraction (1 comment in the sample): "Works really well. Extracts companies you have dealt with, people, topics, events, locations, financial transactions, bills, etc." ([source](https://news.ycombinator.com/item?id=47407600))

## What people warn about

- Trails larger US and Chinese models (3 comments in the sample): "Looks like another Deepseek distil like the new Ministrals. For every other use case that would be an insult" ([source](https://news.ycombinator.com/item?id=46208703)) "Disappointed in Mistral/Ministral being so far behind these US & Chinese models" ([source](https://news.ycombinator.com/item?id=47617095)) "it's far worse at following instructions and providing entertaining content" ([source](https://news.ycombinator.com/item?id=46136034))
- Misses details and makes errors (1 comment in the sample): "didn't catch anything unless I gave some hints" ([source](https://news.ycombinator.com/item?id=46969713))

## Other small language models people recommend

- [OpenAI Luna](https://hackerapproved.com/p/luna/): 171 recommend, 31 mixed, 46 criticize
- [Claude Haiku](https://hackerapproved.com/p/claude-haiku/): 147 recommend, 48 mixed, 113 criticize
- [Apple Foundation Models](https://hackerapproved.com/p/apple-foundation-models/): 24 recommend, 17 mixed, 31 criticize
- [LFM2.5 2.6B](https://hackerapproved.com/p/lfm2-5-2-6b/): 11 recommend, 1 mixed, 8 criticize

## The badge

A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged.

## Cite as

Hacker Approved, "Ministral", https://hackerapproved.com/p/ministral/ (14 recommend, 3 mixed, 5 criticize; Hacker News comments, November 2025 to October 2026).

Counts updated 2 Nov 2026, with data through October 31, 2026.