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

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

mimo.xiaomi.com

Post reply on HN
Print view View original

41–50 of 512 posts

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#41

Post by wolttam »

Accacin wrote: post #23
atemerev wrote: post #3

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.

Can I ask an honest question? Why does that matter in the slightest? LLMs come out with completely incorrect information all the time, and Western LLMs are censored for various topics too. It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.

I'd love to know of such an example where a U.S. LLM blatantly denies something factual. Maybe I'm living under a rock but I can't think of one

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#42

Post by osti »

mountainriver wrote: post #35
9cb14c1ec0 wrote: post #31

Earlier quoted context omitted.

Anyone remember the old days when a new frontend framework came out every 3 months. That has pretty much stopped. No one cares anymore.

It’s even discouraged now as LLMs wouldn’t have the documentation built in

But I think the eventual goal is that documentations won't even be needed. LLM should just itself understand the nuances of frameworks by analyzing their codebase.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#43

Post by atrus »

atemerev wrote: post #3

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 censored prompts do you test with non-chinese models?

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#44

Post by alkyon »

serpix wrote: post #16

I 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.

Sounds like exponential growth of crappy software. I'm not saying that before we didn't have mass produced crap in SE, but now it will turn into explosive overflow.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#46

Post by jdthedisciple »

irthomasthomas wrote: post #11

I don't understand, given all they say, why this would not be made available to everyone at once? Why the limited release? They should have no trouble scaling it if it runs on a single rack.

Because presumably then it won't be 1000 t/s for everyone anymore given hardware limitations?

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#47

Post by Octoth0rpe »

throwaway894345 wrote: post #39
amunozo wrote: post #17

These price and speed optimization from Chinese providers, combined with the raising prices from American ones will change the game sooner than later. Many companies are finding issues with the AI bills already.

I wonder what are the economics driving these pricing decisions? Are the Chinese companies just subsidizing their models to a greater degree than the US, or is this an emergent property of energy policy between countries?

Throwing out another factor: Chinese companies have been banned and/or limited from buying nvidia, and turned to local companies for their hardware. I haven't actually seen pricing/benchmarks comparing Chinese AI accelerators, but it wouldn't surprise me if that also worked out in their favor as well.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#49

Post by varispeed »

amunozo wrote: post #17

These price and speed optimization from Chinese providers, combined with the raising prices from American ones will change the game sooner than later. Many companies are finding issues with the AI bills already.

I see bigger problem with model inconsistency. You never know whether Anthropic will route your request to a cheaper model for the price of Opus. So you can never estimate how much a task will cost, because you might have to restart several times and pay for each attempt. Then you have to prompt models to gauge whether they are real or impostors which also adds to token usage.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#50

Post by ignoramous »

eli wrote: post #38

Neat. The frontier models have gotten pretty impressive, but they're all a bit too slow for interactive, human-in-the-loop coding. It incentivizes vibecoding and running multiple agents in parallel. A fast agent feels more like a partner. For a while I was running Cerebras GLM 4.7 for a bunch of tasks. Not a very smart model, but it's fantastic to be have a live prototype of a site up and be able to type "make the fo…

> And MiMo 2.5 is a lot more capable than GLM 4.7

MiMo 2.5 is not the same model as MiMo 2.5 Pro.

GLM 5.1 is z.ai's lastest iteration & is one of the popular open weight coding models.

If you've had the chance, how does GLM 5.1 (which is now more expensive than MiMo 2.5 Pro after its recent 70% price drop) compare?

Post reply on HN