# Kimi K2.7

Hacker Approved page: https://hackerapproved.com/p/kimi-k2-7/

13 people recommended Kimi K2.7 in Hacker News comments, 4 had mixed feelings and 5 criticized it, November 2025 to October 2026. It was recommended in 4 of 12 months, in 12 threads. It meets the Hacker Approved badge rule.

**Verdict:** People recommend it for strong coding and bug finding at a low cost compared with other models. Critics say it needs more guidance and uses many tokens.

Summary written by Claude from 25 comments.

## Why people recommend it

- Strong coding and bug finding (5 comments in the sample): "the new Kimi K2.7 is looking extremely good, very little doubt it could do it" ([source](https://news.ycombinator.com/item?id=48541820)) "The review catches things humans and two paid options miss." ([source](https://news.ycombinator.com/item?id=49703111)) "Kimi K2.7 is very good - i have been testing it" ([source](https://news.ycombinator.com/item?id=48547481))
- Preferred over other models (4 comments in the sample): "KimiK2.6/2.7, MiMoV2.5/MiMoV2.5-Pro and GLM5.1 will wreck Qwen3.6-27B any day on any task." ([source](https://news.ycombinator.com/item?id=48569991)) "I also have been preferring kimik2.7 more than GLM5.2." ([source](https://news.ycombinator.com/item?id=48928283)) "Kimi K2.5, 2.7 and Deepseek v4 were among my favorites" ([source](https://news.ycombinator.com/item?id=50014997))
- Cost-effective performance (2 comments in the sample): "shows the previous generation of open models (Kimi K2.7) trading blows with the others, cost effectively." ([source](https://news.ycombinator.com/item?id=48986390)) "given the cost/performance" ([source](https://news.ycombinator.com/item?id=48936180))
- Runs well at 4-bit (2 comments in the sample): "K2 2.7 is quite literally designed for 4 bit quantization and runs even better." ([source](https://news.ycombinator.com/item?id=48682110)) "If you're resourceful, you can even run SOTA models." ([source](https://news.ycombinator.com/item?id=48557431))

## What people warn about

- Slow and uses many tokens (2 comments in the sample): "Kimi K2.7 takes about 7x longer to finish the same benchmark tasks as DeepSeek V4 Pro" ([source](https://news.ycombinator.com/item?id=48668297)) "it uses a lot of tokens for quite simple tasks" ([source](https://news.ycombinator.com/item?id=48939478))
- Gets lost on simple tasks (2 comments in the sample): "2.7 also gets totally lost on tasks Sonnet and Opus has no problems with" ([source](https://news.ycombinator.com/item?id=48941041)) "It would run in circles for things that Claude would do in one shot." ([source](https://news.ycombinator.com/item?id=48759928))

## Other open-weight language models people recommend

- [Qwen 3.8 27B](https://hackerapproved.com/p/qwen-3-8-27b/): 804 recommend, 242 mixed, 301 criticize
- [Z.ai GLM](https://hackerapproved.com/p/glm-5-2/): 750 recommend, 181 mixed, 278 criticize
- [Kimi](https://hackerapproved.com/p/kimi-k3/): 652 recommend, 182 mixed, 275 criticize
- [Gemma 4](https://hackerapproved.com/p/gemma-4/): 524 recommend, 120 mixed, 166 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, "Kimi K2.7", https://hackerapproved.com/p/kimi-k2-7/ (13 recommend, 4 mixed, 5 criticize; Hacker News comments, November 2025 to October 2026).

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