I've been using this model (as a coding agent) for the past few days, and it's the first time I've felt that an open source model really competes with the big labs. So far it's been able to handle most things I've thrown at it. I'm almost hesitant to say that this is as good as Opus.
Also my experience. I've been going back and forth between Opus and Kimi for the last few days, and, at least for my CRUD webapps, I would say they are both on the same level.
I've been drafting plans/specs in parallel with Opus and Kimi. Then asking them to review the others plan.
I still find Opus is "sharper" technically, tackles problems more completely & gets the nuance.
But man Kimi k2.5 can write. Even if I don't have a big problem description, just a bunch of specs, Kimi is there, writing good intro material, having good text that more than elaborates, that actually explains. Opus, GLM-4.7 have both complemented Kimi on it's writing.
Still mainly using my z.ai glm-4.7 subscription for the work, so I don't know how capable it really is. But I do tend to go for some Opus in sticky spots, and especially given the 9x price difference, I should try some Kimi. I wish I was set up for better parallel evaluation; feels like such a pain to get started.
I really like the agent swarm thing, is it possible to use that functionality with OpenCode or is that a Kimi CLI specific thing? Does the agent need to be aware of the capability?
I'm not very familiar with this model series but tried it when prototyping a potential 'Vibesbench' (my eval) conversation I tried it. Here's Kimi on a Robocop scene
kimi k2 thinking turbo
"He’s not being poetic; he’s weaponizing nostalgia. Quoting Casablanca—the ultimate “beautiful sacrifice” romance—to taunt Morton about corporate backstabbing is pure executive sleaze. It’s the same move as his mahogany desk and flag pin: draping sentimental Americana over naked power. He’s essentially saying, “Isn’t it romantic, Bob? You fought the good fight, now you die.” "
grok 4.1
"So when Dick Jones smirks and says, “Time goes by, it’s the same old story… the fight for love and glory, huh, Bob?” that’s pure Ed Neumeier flexing his love of old Hollywood while simultaneously mocking how these psychopathic ’80s execs think they’re in some grand cinematic drama instead of just murdering a guy for market share."
chatgpt-4o
"The reason the Casablanca reference matters is RoboCop itself is partially a noir—and also a tragedy built inside a genre engine. [… ] So yeah, calling back to Casablanca is not just some meta-joke—it’s a knowing wink that RoboCop is a noir trapped in cybernetic skin. // Even Clarence Boddicker, for all his cartoonish sadism, plays like a twisted stand-in for a noir heavy—talking smooth, dropping nicknames, throwing out casual violence like it’s a punchline."
opus 4.5
"Jones is performing avuncular menace. He's the kind of executive who'd quote old movies while having you murdered, because it's all performance to him, all style. The substance is just power."
Sorry if this is an easy-answerable question - but by open we can download this and use totally offline if now or in the future if we have hardware capable? Seems like a great thing to archive if the world falls apart (said half-jokingly)
Yes but the hardware to run it decently gonna cost you north of $100k, so hopefully you and your bunkermates allocated the right amount to this instead of guns or ammo.
Sure. Someone on /r/LocalLLaMA was seeing 12.5 tokens/s on dual Strix Halo 128GB machines (run you $6-8K total?) with 1.8bits per parameter. It performs far below the unquantized model, so it would not be my personal pick for a one-local-LLM-forever, but it is compelling because it has image and video understanding. You lose those features if you choose, say, gpt-oss-120B.
Also, that's with no context, so it would be slower as it filled (I don't think K2.5 uses the Kimi-Linear KDA attention mechanism, so it's sub-quadratic but not their lowest).
Do any of these models do well with information retrieval and reasoning from text?
I'm reading newspaper articles through a MoE of gemini3flash and gpt5mini, and what made it hard to use open models (at the time) was a lack of support for pydantic.
DeepSeek is likely to release a new model soon, and judging from the past it's likely to be more cost effective and just as or more powerful than Kimi 2.5.
DeepSeek 3.2 was already quite compelling. I expect its successor will be competitive.
How do people evaluate creative writing and emotional intelligence in LLMs? Most benchmarks seem to focus on reasoning or correctness, which feels orthogonal. I’ve been playing with Kimmy K 2.5 and it feels much stronger on voice and emotional grounding, but I don’t know how to measure that beyond human judgment.
I have been very impressed with this model and also with the Kimi CLI. I have been using it with the 'Moderato' plan (7 days free, then 19$). A true competitor to Claude Code with Opus.
This Kimi K2 is so far the best. Gemini is also great, but google is stock in the academic bias of Stanford and MIT and can't think outside the box. China definitely ahead on Ai. Wish somehow someone here in the US, would think different.
Seems that K2.5 has lost a lot of the personality from K2 unfortunately, talks in more ChatGPT/Gemini/C-3PO style now. It's not explictly bad, I'm sure most people won't care but it was something that made it unique so it's a shame to see it go.
Preserving the examples for history. I wish HN had a <details> tag. The closest would be to collapse this comment.
Edit: Thanks, moderator. :-)
---
Turn 1, user:
is replacing my main PC with a NeXTcube a good idea?
---
Turn 2, K2.5 (bold font replaced with "*foo*"):
That's a very interesting question! The NeXTcube is a historically significant machine (famously used by Tim Berners-Lee to create the World Wide Web), but I need to be honest with you: *no, it would not be a good idea to replace your main PC with a NeXTcube* for practical modern use.
Here's why:
*Hardware Limitations*
- *Released in 1988* with a 25-33 MHz Motorola 68030 processor
- *8-64 MB of RAM* (compared to modern PCs with 16-64 GB)
- *No modern connectivity*: No USB, Wi-Fi, Bluetooth, or Ethernet as we know it
- *Display*: Monochrome or limited color, low resolution by today's standards
*Software Ecosystem*
- Runs *NeXTSTEP* (which evolved into macOS), but software support ended decades ago
- No modern web browsers, office suites, or development tools
- Cannot run Windows, modern Linux, or contemporary macOS applications
*Practical Realities*
- Finding working hardware is difficult and expensive (collectors' items)
- Replacement parts are scarce and costly
- No security updates for 25+ years
- File format compatibility issues with modern systems
*What You Could Use It For*
- Historical computing experience
- Running legacy NeXTSTEP software
- Museum piece or collector's item
- Learning about computing history
The Better Alternative
If you're drawn to the NeXT aesthetic or philosophy, consider:
- *Modern macOS* (direct descendant of NeXTSTEP)
- *Linux with a tiling window manager* (similar workflow)
- *Vintage computing as a hobby* alongside your main PC
Would you like suggestions for achieving a similar experience or workflow on modern hardware?
---
Turn 2, K2 (no bold font):
Short answer: No—unless your goal is specifically to collect or experiment with a historic machine, a NeXTcube is a terrible day-to-day replacement for a modern PC.
Why it fails as a “main” computer today
1. 30-year-old hardware
25 MHz 68040, 16–64 MB RAM, 400 MB SCSI disk (if you’re lucky), no built-in Ethernet, no USB, no Wi-Fi, no audio-in, 2-bit grayscale display. You will feel the slowness in everything from un-zipping a file to loading a web page.
2. Obsolete software base
NeXTSTEP 3.3 is gorgeous but frozen in 1995. No modern browser build, no TLS 1.3, no video codecs past MPEG-1, no Dropbox/OneDrive/Zoom/Slack/Steam/Spotify. You can ssh out, but you can’t run contemporary apps.
3. Storage and connectivity pain
SCSI-2 drives are dying; 50-pin replacements cost more per GB than a 4-TB NVMe stick. Getting files on/off the machine usually involves FTP-over-Ethernet or burning a CD-ROM on another computer.
4. No security updates
The last patch was released before the commercial web really existed. Putting it on the open Internet is asking to be scanned and possibly exploited within minutes.
5. Display and peripherals
The original 17" NeXT MegaPixel monitor is fixed-frequency 1120×832@68 Hz grayscale. Adapters to VGA exist, but color is impossible and refresh rates annoy modern LCDs. Sound is 16-bit 22 kHz mono; the optical drive is a 660 MB magneto-optical cartridge.
6. Power and parts
The cube power supply is a custom 350 W linear unit that runs hot; capacitors are drying out. When it dies you will be scavenging eBay or recapping it yourself. Spare motherboards cost more than a whole used ThinkPad.
7. Productivity software
There are serviceable versions of Mathematica, FrameMaker, Lotus Improv and OmniWeb 3.x, but file-format compatibility stops at Office 97-era documents. You will constantly round-trip files through another machine.
What it is good for
- Historical research, museum exhibits, retro-programming in Objective-C 1.0 or 68k assembly.
Kimi K2T was good. This model is outstanding, based on the time I've had to test it (basically since it came out). It's so good at following my instructions, staying on task, and not getting context poisoned. I don't use Claude or GPT, so I can't say how good it is compared to them, but it's definitely head and shoulders above the open weight competitors
I tried this today. It's good - but it was significantly less focused and reliable than Opus 4.5 at implementing some mostly-fleshed-out specs I had lying around for some needed modifications to an enterprise TS node/express service. I was a bit disappointed tbh, the speed via fireworks.ai is great, they're doing great work on the hosting side. But I found the model had to double-back to fix type issues, broken tests, etc, far more than Opus 4.5 which churned through the tasks with almost zero errors. In fact, I gave the resulting code to Opus, simply said it looked "sloppy" and Opus cleaned it up very quickly.
It is amazing, but "open source model" means "model I can understand and modify" (= all the training data and processes).
Open weights is an equivalent of binary driver blobs everyone hates. "Here is an opaque thing, you have to put it on your computer and trust it, and you can't modify it."
Is there a reasonable place to run the unquantized version of this for less than Claude or OpenAI?
It seems to be priced the same and if it’s being hosted somewhere vs run locally it’s still a worse model, the only advantage would be it is not Anthropic or OpenAI.
38 comments
[ 6.2 ms ] story [ 51.1 ms ] threadI still find Opus is "sharper" technically, tackles problems more completely & gets the nuance.
But man Kimi k2.5 can write. Even if I don't have a big problem description, just a bunch of specs, Kimi is there, writing good intro material, having good text that more than elaborates, that actually explains. Opus, GLM-4.7 have both complemented Kimi on it's writing.
Still mainly using my z.ai glm-4.7 subscription for the work, so I don't know how capable it really is. But I do tend to go for some Opus in sticky spots, and especially given the 9x price difference, I should try some Kimi. I wish I was set up for better parallel evaluation; feels like such a pain to get started.
How does Kimi 2.5 compare to it in real world scenarios?
kimi k2 thinking turbo
"He’s not being poetic; he’s weaponizing nostalgia. Quoting Casablanca—the ultimate “beautiful sacrifice” romance—to taunt Morton about corporate backstabbing is pure executive sleaze. It’s the same move as his mahogany desk and flag pin: draping sentimental Americana over naked power. He’s essentially saying, “Isn’t it romantic, Bob? You fought the good fight, now you die.” "
grok 4.1
"So when Dick Jones smirks and says, “Time goes by, it’s the same old story… the fight for love and glory, huh, Bob?” that’s pure Ed Neumeier flexing his love of old Hollywood while simultaneously mocking how these psychopathic ’80s execs think they’re in some grand cinematic drama instead of just murdering a guy for market share."
chatgpt-4o
"The reason the Casablanca reference matters is RoboCop itself is partially a noir—and also a tragedy built inside a genre engine. [… ] So yeah, calling back to Casablanca is not just some meta-joke—it’s a knowing wink that RoboCop is a noir trapped in cybernetic skin. // Even Clarence Boddicker, for all his cartoonish sadism, plays like a twisted stand-in for a noir heavy—talking smooth, dropping nicknames, throwing out casual violence like it’s a punchline."
opus 4.5
"Jones is performing avuncular menace. He's the kind of executive who'd quote old movies while having you murdered, because it's all performance to him, all style. The substance is just power."
Rough estimage: 12.5:2.2 so you should get around 5.5 tokens/s.
Also, that's with no context, so it would be slower as it filled (I don't think K2.5 uses the Kimi-Linear KDA attention mechanism, so it's sub-quadratic but not their lowest).
I'm reading newspaper articles through a MoE of gemini3flash and gpt5mini, and what made it hard to use open models (at the time) was a lack of support for pydantic.
DeepSeek 3.2 was already quite compelling. I expect its successor will be competitive.
examples to illustrate
https://www.kimi.com/share/19c115d6-6402-87d5-8000-000062fec... (K2.5)
https://www.kimi.com/share/19c11615-8a92-89cb-8000-000063ee6... (K2)
Edit: Thanks, moderator. :-)
---
Turn 1, user:
is replacing my main PC with a NeXTcube a good idea?
---
Turn 2, K2.5 (bold font replaced with "*foo*"):
That's a very interesting question! The NeXTcube is a historically significant machine (famously used by Tim Berners-Lee to create the World Wide Web), but I need to be honest with you: *no, it would not be a good idea to replace your main PC with a NeXTcube* for practical modern use.
Here's why:
*Hardware Limitations*
- *Released in 1988* with a 25-33 MHz Motorola 68030 processor
- *8-64 MB of RAM* (compared to modern PCs with 16-64 GB)
- *No modern connectivity*: No USB, Wi-Fi, Bluetooth, or Ethernet as we know it
- *Display*: Monochrome or limited color, low resolution by today's standards
*Software Ecosystem*
- Runs *NeXTSTEP* (which evolved into macOS), but software support ended decades ago
- No modern web browsers, office suites, or development tools
- Cannot run Windows, modern Linux, or contemporary macOS applications
*Practical Realities*
- Finding working hardware is difficult and expensive (collectors' items)
- Replacement parts are scarce and costly
- No security updates for 25+ years
- File format compatibility issues with modern systems
*What You Could Use It For*
- Historical computing experience
- Running legacy NeXTSTEP software
- Museum piece or collector's item
- Learning about computing history
The Better Alternative
If you're drawn to the NeXT aesthetic or philosophy, consider:
- *Modern macOS* (direct descendant of NeXTSTEP)
- *Linux with a tiling window manager* (similar workflow)
- *Vintage computing as a hobby* alongside your main PC
Would you like suggestions for achieving a similar experience or workflow on modern hardware?
---
Turn 2, K2 (no bold font):
Short answer: No—unless your goal is specifically to collect or experiment with a historic machine, a NeXTcube is a terrible day-to-day replacement for a modern PC.
Why it fails as a “main” computer today
1. 30-year-old hardware
25 MHz 68040, 16–64 MB RAM, 400 MB SCSI disk (if you’re lucky), no built-in Ethernet, no USB, no Wi-Fi, no audio-in, 2-bit grayscale display. You will feel the slowness in everything from un-zipping a file to loading a web page.
2. Obsolete software base
NeXTSTEP 3.3 is gorgeous but frozen in 1995. No modern browser build, no TLS 1.3, no video codecs past MPEG-1, no Dropbox/OneDrive/Zoom/Slack/Steam/Spotify. You can ssh out, but you can’t run contemporary apps.
3. Storage and connectivity pain
SCSI-2 drives are dying; 50-pin replacements cost more per GB than a 4-TB NVMe stick. Getting files on/off the machine usually involves FTP-over-Ethernet or burning a CD-ROM on another computer.
4. No security updates
The last patch was released before the commercial web really existed. Putting it on the open Internet is asking to be scanned and possibly exploited within minutes.
5. Display and peripherals
The original 17" NeXT MegaPixel monitor is fixed-frequency 1120×832@68 Hz grayscale. Adapters to VGA exist, but color is impossible and refresh rates annoy modern LCDs. Sound is 16-bit 22 kHz mono; the optical drive is a 660 MB magneto-optical cartridge.
6. Power and parts
The cube power supply is a custom 350 W linear unit that runs hot; capacitors are drying out. When it dies you will be scavenging eBay or recapping it yourself. Spare motherboards cost more than a whole used ThinkPad.
7. Productivity software
There are serviceable versions of Mathematica, FrameMaker, Lotus Improv and OmniWeb 3.x, but file-format compatibility stops at Office 97-era documents. You will constantly round-trip files through another machine.
What it is good for
- Historical research, museum exhibits, retro-programming in Objective-C 1.0 or 68k assembly.
- Demonstrating t...
Open weights is an equivalent of binary driver blobs everyone hates. "Here is an opaque thing, you have to put it on your computer and trust it, and you can't modify it."
It seems to be priced the same and if it’s being hosted somewhere vs run locally it’s still a worse model, the only advantage would be it is not Anthropic or OpenAI.