Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kimi K2.7-Code: open-source coding model with better token efficiency

huggingface.co

Post reply on HN
Print view View original

211–220 of 254 posts

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#211

Post by kube-system »

kennywinker wrote: post #91
esafak wrote: post #72

Earlier quoted context omitted.

I don't think "Chinese" is pejorative in this context any more than "American" is. They are one of the two ecosystems. What's wrong with saying "Japanese cars" today?

> What's wrong with saying "Japanese cars" today? Only that it’s a fairly meaningless grouping. When japan first entered the car market in north america there might have been some commonality, but now what characteristics do they share that some american cars don’t have? They’re not even imported a lot of the time. Given that, it does start to feel tinged with racism if someone insists on grouping things together tha…

> When japan first entered the car market in north america there might have been some commonality, but now what characteristics do they share that some american cars don’t have?

They're unique in that they even make a regular passenger car. American manufacturers only make SUVs and a couple of sports/luxury cars. They basically gave up because the Camry/Corolla/Accord/Civic ate their lunch.

The cheapest sedan you can get from an American brand is the Cadillac CT4.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#212

Post by saratogacx »

nullbio wrote: post #33
yanis_t wrote: post #2

I was wondering how does Anthropic and likes keep competitive when Opus is ($5 / $25) 5x times more expensive compared to Kimi K2.6 ($0.7 / $3.4) or other Chinese models, while being only marginally better. My theory is that US enterprise just can't send data to Chinese and that's understandable, but is that "the moat"?

I think none of them having a defacto and high quality English focused cli is a big part of it. None of the Chinese models I've tried have worked well in opensource cli's. Granted, I've only tried a few, but still...

I've been using charm's Crush with GLM for several months and it's been working great. I've only seen it shift to non-english once and it was already in a wonky state when it flipped.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#213

Post by apitman »

MaKey wrote: post #203
ignoramous wrote: post #182

Earlier quoted context omitted.

> I've kind of given up on the routers for "free" inference, as you would expect, they tend to give you sub-par thinking because they are obviously trying to conserve as much inference as possible. Xiaomi MiMo ($6/mo: https://platform.xiaomimimo.com/token-plan ) & Alibaba Qwen ($50/mo: https://www.alibabacloud.com/en/campaign/ai-scene-coding ) have generous limits on fixed subscriptions.

So does Opencode Go ($10/mo: https://opencode.ai/go ) for DeepSeek v4 Flash and MiMo 2.5.

That looks pretty nice. How does it compare cost-wise to just using OpenRouter?

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#214

Post by apitman »

odiroot wrote: post #112
trollbridge wrote: post #32

Earlier quoted context omitted.

I am extremely happy with ohmypi, but you could use OpenCode or just keep using Claude Code! DeepSeek-V4-Pro is adequate plus use DS4-Flash for tasks or other small activity you’d use Haiku or Sonnet for. Go sign up with $10 prepaid. OpenCode Go - go sign up with $5 for a month and use Qwen-3.7-Max for design/plan/architecture or difficult troubleshooting. Feels closer to Opus 3.6 or 3.7 than DeepSeek, closest I’ve f…

> I am extremely happy with ohmypi, but you could use OpenCode or just keep using Claude Code! What's the benefit of using OMP over OpenCode? Just the sheer amount of options in OMP overwhelmed me. But I also use both via ACP in Zed so the CLI itself doesn't matter much.

OMP is a fork of Pi[0], which is my preferred harness. Feels solid and minimal. I don't even use any extensions, skills, or modifications. Usually don't even use an AGENTS.md. Just create a small spec.md and/or plan.md for most experiments.

[0]: https://pi.dev/

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#215

Post by apitman »

jackdoe wrote: post #11

I think there is some threshold after which "best" model doesn't matter, we are not that far from it. Fable now is really good, in a year or so, if Kimi catches up, even if Fable6 is much better, I think I will use kimi at 1/10th of the price. I said that about opus 4.5 at the time, thinking "this is so good, in 6-12 months the Chinese models will be as good and cheap, I will use them", but I was wrong.. I pay premiu…

I think the next frontier for competition is speed. Instead of constantly context-switching between multiple agents that I have working on various tasks, I want a single agent that can rip through any prompt in a few seconds, so I can stay in flow on a single task.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#216

Post by arcanemachiner »

apitman wrote: post #213
MaKey wrote: post #203

Earlier quoted context omitted.

So does Opencode Go ($10/mo: https://opencode.ai/go ) for DeepSeek v4 Flash and MiMo 2.5.

That looks pretty nice. How does it compare cost-wise to just using OpenRouter?

The Go plan essentially gives you $50 of inference for $10 per month ($5 for the first month).

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#217

Post by wgd »

knollimar wrote: post #169
kouteiheika wrote: post #128

Earlier quoted context omitted.

The model is natively quantized (i.e. it was trained that way in the first place, so this is not a post-training quantization which degrades performance).

Isn't it not completely quantized? I thought there were some dense parts but most is int4?

Often in MoE models the experts are quantized while the shared portions, being a much smaller part of the network with greater impact, are kept at higher or full precision. Not familiar with the Kimi QAT approach specifically but it's likely they do this.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#218

Post by ignoramous »

arcanemachiner wrote: post #216
apitman wrote: post #213

Earlier quoted context omitted.

That looks pretty nice. How does it compare cost-wise to just using OpenRouter?

The Go plan essentially gives you $50 of inference for $10 per month ($5 for the first month).

$60/mo currently: https://opencode.ai/docs/go/#usage-limits

Their limits are staggered: 5h (max $12), weekly ($30), monthly ($60).

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#219

Post by monksy »

trollbridge wrote: post #32
shreedx wrote: post #10

I would really love to know if anyone has any experience with something like opencode + Kimi K2.6/2.7 now compared to Claude Code. What is better, what is worse, what is the cost comparison. I am currently paying $100 for the 5x Max plan, but Fable is running through the usage limits quite drastically and I cannot really say it's night and day compared to Opus. Also, I use this mostly for my side projects, so the $10…

I am extremely happy with ohmypi, but you could use OpenCode or just keep using Claude Code! DeepSeek-V4-Pro is adequate plus use DS4-Flash for tasks or other small activity you’d use Haiku or Sonnet for. Go sign up with $10 prepaid. OpenCode Go - go sign up with $5 for a month and use Qwen-3.7-Max for design/plan/architecture or difficult troubleshooting. Feels closer to Opus 3.6 or 3.7 than DeepSeek, closest I’ve f…

I just switched from Llama.cpp to Llama swap with the help of codex. It was great.

I need to try the DSv4 stuff sometime.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#220

Post by WarmWash »

SubiculumCode wrote: post #145
WarmWash wrote: post #73

Earlier quoted context omitted.

[flagged]

For those that don't like calling them CCP models, may I remind you, the CCP won't let Chinese AI researchers out of the country any more without securing approval first[1]. [1] https://www.tomshardware.com/tech-industry/artificial-intell...

C'mon shills, get on the whataboutism...
Post reply on HN