Introducing HRM-Text.
@Sapient_Int6.2K followers
519,365 views
34 Comments
Comments from the original post on X (Twitter)

@Sapient_Int
Download HRM-Text 🔗 Github: Hugging Face:
275 likes

@flaviusburca
Am I missing something ? HRM-Text is trained on a corpus where every benchmark's training set is present and often upsampled 10×. Of course you hit the same benchmark score with 150× less data when 150× more of your data is on-distribution for the eval.
32 likes

@ai_explorer25
Watched it twice. The $1k pretraining number is going to do more for independent research than any open-weights release this year
27 likes

@williawa
Those are impressive results. Any reason you didn’t scale it up? It’s a bit strange to have a flagship that trains for a thousand dollars.
23 likes

@flaviusburca
The training mix (data_io) includes GSM8k-train ×10, MATH-train ×10, and FLAN (which contains HellaSwag/ARC/BoolQ/Winogrande train splits). Most of the 150× saving is the data mix, not the architecture. But I do have to applaude the ingenious H/L split :)
12 likes

@pigeon__s
those are the numbers for Qwen3 Qwen3.5s dataset size has not been disclosed and if you really believe in this AND its so cheap you should scale it up to at least 32B range and get llama.cpp compatability otherwise nobody can even use it or care about it
11 likes

@aiCrof
Very interesting! What about for bigger models larger than 1b?
11 likes

@DevHunterYZ
$1000 for a 1B parameter is excessive. I full pretrained my 1.5B RLM model with an RTX Pro 6000 for 13 hours. It cost less than $4(with Google Colab).
8 likes

@knowixbuilds
looks promising, can't wait to try it out. I really need a small parameter model that I can run on my old PC
8 likes

@brunao_eth
training a 1B model in a day for $1k is insane the barrier to AI research just dropped through the floor
7 likes

@ritteradam
Amazing result, this is where I don't understand why you didn't start a company instead of letting the LLM companies just use it to train much smarter models.
7 likes

@Everlier
This release is incompatible with me going to sleep in time
5 likes

@JulesNetX
Brilliant. Hierarchical dual-timescale reasoning in a 1B model that beats far larger ones on 40B tokens is exactly the efficiency breakthrough we need. This is how we get to real intelligence, not just scale.
5 likes

@himanshustwts
awesome work, congrats!
4 likes

@ziwenxu_
wait it's only 1B and trained in a day?? That's wild
4 likes

@yur_o_0
"chain-of-thought" slander for 5 whole mins. great approach, moving from grid-based puzzling in HRM to implementing latent recursive reasoning in language modelling through HRM-text.
4 likes

@Sapient_Int
Paper:
4 likes

@BruzWJ
one day and a thousand bucks is wild, but comparable models is doing a lot of work in that claim what evals are you running and what's the accuracy gap?
3 likes

@thePM_001
That's super, so maybe we can use our new approach of cloning the LLM behavioural shadow here for only 10 USD and then inference it with CPU. Have to investigate.
3 likes

@yulikay
I’ve been using my personal agent for a while now So this could be a game-changer!
3 likes













