Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
AxionLab-official 
posted an update 1 day ago
Post
7056
THIS IS CRAZY! THE MODEL ON THE IMAGE(Supra-50M-Reasoning) answered correctly and its QUANTIZED IN 2BIT! THE RESPONSE IS CORRECT, IN A 15MB SIZE FILE!

Yes it is , Tell me is the model consistent with it ? Like out of how many prompt did model get right answer ?

·

I mean, like, we are talking about a 50M model here. That thing, already in full precision, can barely do basic math. On 2 bits, even a single question being right is impressive.

Great

interesting

It got my His information wrong—and this was INT8. Unworthy.
Screenshot 2026-06-06 051601
But seriously lmao what is this??
Screenshot 2026-06-06 052258

·

It turns out that you can cherry pick results, post an image, and act like it generalizes

I’m curious how it arrived https://github.com/space-bacon/SRT

I've wondered, if a sufficiently reasoned model can get away with missing a lot of data because it can reason it out, and thus the smaller size may be worth it to be faster/leaner (even if it needs more tokens to reason the solution).