# MiniMax M2 154 Hacker News commenters recommended MiniMax M2 and 49 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months. It meets the Hacker Approved badge rule. **Verdict:** An open-weight coding model that runs locally and comes close to Sonnet and Opus at a fraction of the price; critics cite slowness and heavy token use. ## Why people recommend it - Much cheaper than frontier models (8 comments): "It's quite cheap and seems to be better than Gemini 3 Flash, but it gets really pricy as the context fills up" ([source](https://news.ycombinator.com/item?id=47739824)) "They are almost as smart but 10x cheaper and their attitude towards subscribers is use where you want." ([source](https://news.ycombinator.com/item?id=47117645)) "has really hit the sweet spot of being very cheap, though more than flash, but I'd also very capable" ([source](https://news.ycombinator.com/item?id=48519392)) - Near-SOTA coding capability (7 comments): "You get an open model which is a 95% of Opus 4.6 quality and 80% cheaper in most inference providers" ([source](https://news.ycombinator.com/item?id=47374005)) "M2.1 is 10x cheaper than Sonnet for example, but practically fairly close in capabilities" ([source](https://news.ycombinator.com/item?id=46548457)) "I am pretty sure MiniMax M2.7 would be much better." ([source](https://news.ycombinator.com/item?id=47738396)) - Runs locally on ordinary hardware (4 comments): "The open models are getting so good that what we get at the end of this year will be "good enough" locally for years" ([source](https://news.ycombinator.com/item?id=46512264)) "As far as I can tell Minimax M2.7 is better than anything available a year ago, but it runs on an ordinary PC." ([source](https://news.ycombinator.com/item?id=47929228)) "run something like MiniMax M2.1 to get last-gen performance at something resembling usable speed" ([source](https://news.ycombinator.com/item?id=46767461)) - Efficient, fewer tokens per answer (2 comments): "Minimax M2.7 is also surprisingly not that slow, and in some ways faster as it seems to get things right with less thinking output." ([source](https://news.ycombinator.com/item?id=47869547)) "MiniMax M2.7 230B is in some ways faster (way fewer tokens to arrive at an answer) even though it is much larger" ([source](https://news.ycombinator.com/item?id=48392488)) ## What people warn about - Slow inference speed (4 comments): "I'm also sure your prefill is slow enough to make the model mostly unusable, even at smallish context windows" ([source](https://news.ycombinator.com/item?id=46742606)) "Minimax has been a strong player in our tests, if they managed to solve the inference speed issue" ([source](https://news.ycombinator.com/item?id=50156021)) "run something like MiniMax M2.1 to get last-gen performance at something resembling usable speed" ([source](https://news.ycombinator.com/item?id=46767461)) - Burns through many tokens (3 comments): "performed really poorly in practice and burned through hundreds of thousands of reasoning tokens for each request" ([source](https://news.ycombinator.com/item?id=47306753)) "Minimax/Composer have this habit of extensive thinking and it is said to be their strength" ([source](https://news.ycombinator.com/item?id=47664160)) "it seems to use A LOT of tokens and it's the slowest model that we've tested for the exam" ([source](https://news.ycombinator.com/item?id=50161518)) - Weak at following instructions (2 comments): "Not as great as following instructions as Claude models and can get lost, but still "good enough"." ([source](https://news.ycombinator.com/item?id=46388644)) "M2.1 is extremely bad at writing tests and following instructions from a .md, I've found" ([source](https://news.ycombinator.com/item?id=46506860)) - Below Opus-level output quality (2 comments): "this one far underperforms relative to GLM 5.3 from every test I've done for real-world cybersecurity tasks" ([source](https://news.ycombinator.com/item?id=50162481)) "I found it to be decent. Did not really seem comparable to Opus 4.5 for "quality" output." ([source](https://news.ycombinator.com/item?id=47429080)) ## Alternatives hackers recommend - [Qwen 3.8 27B](https://hackerapproved.com/p/qwen-3-8-27b.md): 1173 recommend - [Z.ai GLM](https://hackerapproved.com/p/glm-5-2.md): 1043 recommend - [Kimi](https://hackerapproved.com/p/kimi-k3.md): 931 recommend - [Gemma 4](https://hackerapproved.com/p/gemma-4.md): 713 recommend - [Qwen](https://hackerapproved.com/p/qwen.md): 474 recommend ## Where to get it - [Visit the official site](https://www.minimax.io/) ## Cite as Hacker Approved, "MiniMax M2", https://hackerapproved.com/p/minimax-m2-7/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).