I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.
Which ones fail?
Deepkseek
MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
101–110 of 512 posts
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#102Earlier quoted context omitted.
Sliding window for the draft model, not for the main. 42B for active params because it’s a sparse MoE which is a common technique for the larger models to not get bottlenecked by memory bandwidth.
Seems to be for both according to the spec [0], maybe it's wrong though. 128 sounds really tiny, I wonder if they mean some kind of blocks? [0] https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash#4...
No
> It uses 384 routed experts (top-8) with hybrid attention (full-attention + sliding-window 128 at 6:1 ratio) over 70 layers (1 dense + 69 MoE)
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#103A few things in life I can't fully grasp why they are so sought after. One is that constant need to exhibit growth. As if being massive and staying as massive is not good enough, one has to always and continuously grow. The other is constant speed increases. We're already operating at 50x speed. My output is much wider and so much faster, I am sometimes my own bottleneck. And now as if that is not enough we want more…
I remember when I had to wait minutes to get a high resolution image over a dialup connection. When computer and communications hardware advanced enough that I could get 30 high resolution images every second, there were brand new uses. In the case of LLMs, I could imagine that much faster operations allow you to introduce them as parts of systems that need to react to the real world at high speed, like factory equip…
The example in the video was a generation of a dashboard app of some sort. I can do that with a "normal speed" Claude in a few minutes. The difference is a few minutes. This is compared to a few weeks in old school development time. I don't have a problem with taking it a little "slow" (as in - few minutes) and lending my thought to it rather than just going for fast generation and who knows what's inside. I get your use case, but this is a specialised one, and not the one 90% of people will think of - everyone want that fast app in 12 seconds... Or so it seems from me being downvoted on that comment.
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#104Fast AI seems genuinely exciting and somewhat unsettling to me. Right now Claude is faster than me on some tasks but we’re at least close. I have a prompt to clean up a PR that’s been running for 1h now and I expect it to take another few. It’s hard to imagine how the workflow would look like if it was near-instant. On the one hand, it might be easier to focus. Some prompts take so long that I start to multitask and…
I'm using Deepseek-v4-pro as my main model and this is sometimes pretty annoying, I have to do some easy boring task, think "I'll just leave the agent to do it and go take a nap", but it's already done writing the code before I even walk away from the computer
Do you mean Flash and not Pro? I haven't tried it personally, but according to OpenRouter, the fastest DeekSeep V4 Pro providers are only ~50tps. That's slower than Claude Opus.
https://openrouter.ai/deepseek/deepseek-v4-pro?sort=throughp...
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#105Earlier quoted context omitted.
asking for curiosities sake. What kind of PR loop are you running that takes a few hours?
not OP but usually for me this means long verification loop; waiting 10min on CI checks, that kind of thing, rather than actual 1hr wall clock of token generation
Or slow MCP servers that are waiting on HTTP calls from APIs, playwright/other UI instrumentation, etc.
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#106Earlier quoted context omitted.
MiMo and DeepSeek are not cheap. Anthropic and OpenAI are expensive for what they provide.
The Chinese "Neijuan" is real & well reported: https://www.reuters.com/business/autos-transportation/what-i... It is another thing the BigLabs accuse open weight models of benefiting from distillation & other techniques & essentially avoid higher training costs (which typically bleed into bills end users pay for inference). Ex A: https://www.anthropic.com/research/2028-ai-leadership Ex B: https://www.reuters.com/worl…
We buy cheap Chinese goods all the time. Absolutely nothing wrong with that.
In this case, at least it’s threatening multimillion dollar salary jobs instead of entire towns of working class people in America or Mexico.
And the Chinese labs actually release their weights. You could call it… open AI.
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#107I may sound like a shill, but exponential growth and all. We are going to get near instant software from prompt, multiple ones and then choose the best one. Discussions about choosing a library with the best syntactic sugar method naming is just as crazy as suggesting we type in assembly.
> Discussions about choosing a library with the best syntactic sugar method naming is just as crazy as suggesting we type in assembly.
I have a more hopeful take. As AIs improve and get faster we can more quickly and iteratively improve code which we may have historically avoided due to the work involved.
I know i've made several refactors that would have otherwise been insane lifts. Not only because the work involved but because sometimes you don't know if it will work, and so you have a sort of double friction; you don't know if it will even succeed. With an AI you can just throw it at the refactor to see if it runs into a problem all while you're having a coffee break or w/e.
In general AI is going to enable humanity to be more extreme versions of itself. For good and bad. I suspect more bad than good, though.
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#108Earlier quoted context omitted.
Because this never gets brought up about US models, which have just as much censorship as the Chinese ones.
Please educate us - which accurate and provable events in history are censored by US based LLMs as part of a government enforced reeducation campaign?
Does it even matter which agendas get censored? Like why won't my Claude tell me how to make sarin gas? I'd genuinely like to understand it. Sure, you can always reach for a justification saying "preventing terrorism" but the same argument can be made by Chinese AI labs.
What actually matters is that the mere tool is withholding information at all, and that the boundaries were set by whoever designed it.
Dont get me wrong I've been an advocate of this stuff (I carry two phones, one with GOS for my personal use and the other for ID verifications). However, without reasoning, you just can't see it, because you're as biased and propagandized as anyone in China.
Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#109Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
#110No note about the specific GPU they use. One might speculate. B200? H200? H100?