\
  The most prestigious law school admissions discussion board in the world.
BackRefresh Options Favorite

Review of IBM's new open weight model by a bigtech bro

I had a shortish exploratory chat with Granite4.1:8b tonight...
Plum rehab
  04/30/26
who cares
spruce reading party meetinghouse
  04/30/26
I understood like half of that. Explain it like I don't read...
Sticky glittery water buffalo
  04/30/26
It's designed to be fast and it was trained on high quality ...
Plum rehab
  04/30/26
What does "no reasoning" mean?
Sticky glittery water buffalo
  04/30/26
Everyone thought they needed reasoning models to get the bes...
Plum rehab
  04/30/26
What does that mean? Doesn't it need to do reasoning to foll...
Sticky glittery water buffalo
  04/30/26
The model still has to follow intermediate steps during prom...
Plum rehab
  04/30/26
Yeah ofc, I just didn't know what "reasoning" mean...
Sticky glittery water buffalo
  04/30/26
Like how chat gpt and claude for "hard problems" w...
Flushed Tripping Ticket Booth Quadroon
  04/30/26
Got it, I thought it might mean that. I totally believe it c...
Sticky glittery water buffalo
  04/30/26
Would never use something that has "deterministic outpu...
Flushed Tripping Ticket Booth Quadroon
  04/30/26
I have news for you about women
heady aquamarine university main people
  04/30/26
what tokens/sec are you getting
beady-eyed slap-happy wrinkle bawdyhouse
  04/30/26


Poast new message in this thread



Reply Favorite

Date: April 30th, 2026 10:54 PM
Author: Plum rehab

I had a shortish exploratory chat with Granite4.1:8b tonight.

It is a good model. The outputs feel something akin to deterministic which reflects the enterprise deployment IBM is shooting for. Input -> Output. The voice is pleasant and not overly beepboop robot. It hyperfixates on patterns (one message with a list kicks off 5 more) but it responses really well to faux system messages correcting it. The world knowledge is good and nuanced for an 8b model.

If I had a no-human-in-the-loop pipeline for evaluations or content parsing or something I’d 100% reach for Granite 4.1 first. It’s like,,, instruct tuned but only enough to accomplish its intended goal.

——

Oh! And! No reasoning! As an engineered design constraint. Neat!

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856001)



Reply Favorite

Date: April 30th, 2026 10:56 PM
Author: spruce reading party meetinghouse

who cares

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856010)



Reply Favorite

Date: April 30th, 2026 10:56 PM
Author: Sticky glittery water buffalo

I understood like half of that. Explain it like I don't read hackernews

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856011)



Reply Favorite

Date: April 30th, 2026 11:00 PM
Author: Plum rehab

It's designed to be fast and it was trained on high quality data. IBM really went their own direction

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856026)



Reply Favorite

Date: April 30th, 2026 11:02 PM
Author: Sticky glittery water buffalo

What does "no reasoning" mean?

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856029)



Reply Favorite

Date: April 30th, 2026 11:09 PM
Author: Plum rehab

Everyone thought they needed reasoning models to get the best chat experience, but now with agentic harnesses the reasoning becomes a waste of tokens. I have it disabled in my Hermes Agent because it's too fuckin slow. IBM basically just saved us all from having to manually disable it

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856064)



Reply Favorite

Date: April 30th, 2026 11:10 PM
Author: Sticky glittery water buffalo

What does that mean? Doesn't it need to do reasoning to follow instructions?

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856068)



Reply Favorite

Date: April 30th, 2026 11:28 PM
Author: Plum rehab

The model still has to follow intermediate steps during prompt processing, people are just finding more efficient ways to do it. One model (I forget which one) keeps the entire prompt intact at each layer.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856095)



Reply Favorite

Date: April 30th, 2026 11:54 PM
Author: Sticky glittery water buffalo

Yeah ofc, I just didn't know what "reasoning" meant and was too lazy to search

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856136)



Reply Favorite

Date: April 30th, 2026 11:33 PM
Author: Flushed Tripping Ticket Booth Quadroon

Like how chat gpt and claude for "hard problems" will go into a "chain of thought" where it "reasons". I turn it off for basic chats and only use it when I'm having it solve something difficult. Also sometimes it makes it stupider believe it or not. Also way faster without it.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856103)



Reply Favorite

Date: April 30th, 2026 11:53 PM
Author: Sticky glittery water buffalo

Got it, I thought it might mean that. I totally believe it could make it stupider in some cases. I'll turn that off on the ones I use and see if the results are better.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856134)



Reply Favorite

Date: April 30th, 2026 11:31 PM
Author: Flushed Tripping Ticket Booth Quadroon

Would never use something that has "deterministic outputs"

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856098)



Reply Favorite

Date: April 30th, 2026 11:36 PM
Author: heady aquamarine university main people

I have news for you about women

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856105)



Reply Favorite

Date: April 30th, 2026 11:55 PM
Author: beady-eyed slap-happy wrinkle bawdyhouse

what tokens/sec are you getting

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2Elisa#49856142)