Kimi K2.7
Hacker ApprovedRanked 25 of 39 open-weight language models by recommenders
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.
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.
23 people gave an opinion
- recommend it
- 18
- criticize it
- 5
- approval share
- 78%
Recommended in 5 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: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 18 people recommend itNeeds 10 or more, met.
- 3.6 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, 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 coding and bug finding
“the new Kimi K2.7 is looking extremely good, very little doubt it could do it”
Comment from 15 Jun 2026 in “Anthropic's Safety Superpower” “The review catches things humans and two paid options miss.”
Comment from 14 Sep 2026 in “GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?” “Kimi K2.7 is very good - i have been testing it”
Comment from 15 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?” - Comment from 16 Jun 2026 in “Feds freaked over Fable 5 after simple 'fix this code' prompt, not jailbreak”
- Comment from 14 Jun 2026 in “Ask HN: Which cheap Chinese LLM are you using?”
Preferred over other models
“KimiK2.6/2.7, MiMoV2.5/MiMoV2.5-Pro and GLM5.1 will wreck Qwen3.6-27B any day on any task.”
Comment from 17 Jun 2026 in “GLM-5.2 is the new leading open weights model on Artificial Analysis” “I also have been preferring kimik2.7 more than GLM5.2.”
Comment from 15 Jul 2026 in “Inkling: Our Open-Weights Model” “Kimi K2.5, 2.7 and Deepseek v4 were among my favorites”
Comment from 9 Oct 2026 in “Why isn't the industry freaking out about DeepSeek 4.1 Flash?” - Comment from 15 Jul 2026 in “Inkling: Our Open-Weights Model”
Cost-effective performance
“shows the previous generation of open models (Kimi K2.7) trading blows with the others, cost effectively.”
Comment from 20 Jul 2026 in “Who's Afraid of Chinese Models?” “given the cost/performance”
Comment from 16 Jul 2026 in “Kimi K3 is now live” Runs well at 4-bit
“K2 2.7 is quite literally designed for 4 bit quantization and runs even better.”
Comment from 26 Jun 2026 in “Apple increases MacBook and iPad prices by 20%” “If you're resourceful, you can even run SOTA models.”
Comment from 16 Jun 2026 in “Running local models is good now”
What people warn about
Each mark is one comment
Slow and uses many tokens
“Kimi K2.7 takes about 7x longer to finish the same benchmark tasks as DeepSeek V4 Pro”
Comment from 25 Jun 2026 in “GLM-5.2 is the step change for open agents” “it uses a lot of tokens for quite simple tasks”
Comment from 16 Jul 2026 in “Kimi K3 is now live” Gets lost on simple tasks
“2.7 also gets totally lost on tasks Sonnet and Opus has no problems with”
Comment from 16 Jul 2026 in “Kimi K3 is now live” “It would run in circles for things that Claude would do in one shot.”
Comment from 2 Jul 2026 in “Kimi K2.7 Code is generally available in GitHub Copilot”
Other open-weight language models people recommend
The four most recommended other open-weight language 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 |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B | 1,173 | 426 | 73% | 13 | 2 mo32 owners | Approved |
| Z.ai GLM | 1,043 | 384 | 73% | 13 | 2 mo52 owners | Approved |
| Kimi | 931 | 359 | 72% | 13 | 1 mo26 owners | Approved |
| Gemma 4 | 713 | 249 | 74% | 13 | 1 mo14 owners | Approved |
| Kimi K2.7This page | 18 | 5 | 78% | 5 | — | Approved |
What people said
All 25 comments that mention it, newest first. Each links to the original comment.
“Kimi K2.5, 2.7 and Deepseek v4 were among my favorites”
“The review catches things humans and two paid options miss.”
“Kimi K2.7 (April) not K2.7-code (June) or K3 (July).”
“If I were to anthropomorphize the thinking traces of K2.7, I would call it nervousness, bordering on fear”
“Kimi k2.7 does require a bit more of guidance but still better experience than opus 4.8.”
“shows the previous generation of open models (Kimi K2.7) trading blows with the others, cost effectively.”
“I used K2.7 to reverse engineer a protocol from Wireshark packages. No complaints.”
“Very competent at mapping out flows and patterns, working in tandem with me too implement what I wanted to implement.”
“2.7 also gets totally lost on tasks Sonnet and Opus has no problems with”
“it uses a lot of tokens for quite simple tasks”
“given the cost/performance”
“I also have been preferring kimik2.7 more than GLM5.2.”
“I find myself using KimiK2.7 half of the time”
“It would run in circles for things that Claude would do in one shot.”
“hopefully I can use Kimi K2.7 by then”
“Kimi k2.7 code seems to have extra training against cyber security capabilities”
“K2 2.7 is quite literally designed for 4 bit quantization and runs even better.”
“Kimi K2.7 takes about 7x longer to finish the same benchmark tasks as DeepSeek V4 Pro”
“you have glm 5.2, kimi k2.7,mimo v2.5 pro and deepseek v4”
“KimiK2.6/2.7, MiMoV2.5/MiMoV2.5-Pro and GLM5.1 will wreck Qwen3.6-27B any day on any task.”
“If you're resourceful, you can even run SOTA models.”
“it'll find issues and propose reasonable fixes”
“Kimi K2.7 is very good - i have been testing it”
“the new Kimi K2.7 is looking extremely good, very little doubt it could do it”
“kimi k2.7 code looks great on this ranking”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.