Feel free to move this to wherever, I don't really expect to see a review on this latest woke media piece :
![]()
Feel free to move this to wherever, I don't really expect to see a review on this latest woke media piece :
![]()
Surprised QWEN 3.6 27B came out yesterday, and as expected it was a decent improvement :
From INT 42 released a couple months ago to INT 46, so nearly a 10% bump.
Should see QWEN 3.6 9B next week based on the rate of these recent releases.
A bit over a year later and just an (amazing) update on where things have progressed too since Jan/Feb 2025.
Based on updated metrics :
Recall on previous posts (above) this thread how ground breaking this model was, and I'm talking about the 8B (8 Billion) parameter model, this rating is on the 528B (685B ?) parameter model.
19.
These are the current (as of a few days ago) rankings (it's outdated from things I've seen) :
Note, the Deepseek on the above graph is Deepseek V3.2, not the R1 from last Jan/Feb.
The above are the best of the subscription models ($).
I've been running this one locally (27B) as that is the best I can do based on INT and VM memory available :
(These are all free at 40B or less for local running by the way).
27B is very slow (VM only, no GPU processing) on my system, but has been extremely impressive.
Still, at more than twice the INT of the Deepseek R1 528B model it is quite tolerable for what I'm testing on it.
The 9B model is quite a bit quicker, and while the "Intelligence" rating is a bit lower than the 27B, it is still quite amazing, and far outperforms the Deepseek 528B model from a little over a year ago.
Just for reference since I posted the subscription models, these are the current best of the free (local if you can run them) models :
Note, the above are sorted more by parameters than intelligence rating - just the way the site is set up.
So 57 INT for the best subscription model vs 54 INT for the best Open source model - it's getting incredibly close providing you have the resources.
I should also add the caveat that some models perform better at certain tasks than others, and that the above is a composite overall assessment.
I should note that there are also hybrids, meaning a mix of two or more models into one model.
The latest I've seen is a mix of QWEN3.5 (9B) & GLM5.1 (9B) (distilled models) coming in at 18B, which supposedly outperforms QWEN3.5 27B (3.5 27B is better than 3.5 35B surprisingly).
QWEN 3.6 35B was just released yesterday or the day before and is on par or marginally better than QWEN 3.5 27B.
Expecting QWEN 3.6 27B to be markedly better, but may be a week or two out yet.
Current best moderate requirement free model looks to be the hybrid QWEN/GLM 18B, which is actually mind boggling.
Once QWEN 3.6 27B comes out, I expect that to be the king for free moderate capacity systems.
QWEN 3.6 9B should be a week or two behind 27B, but I expect it to be extremely performant, possibly twice the level of Deepseek R1 528B from just over a year ago.
There has been some incredible progress made in the last year on these systems.
I believe Anthropic, and maybe others have turned over (self) programming their models to the AI itself (scary) - I may have more on this later.
If this is truly this case, i would expect the pace of progress on these models to increase beyond what they have already over the past year.
Well it happens every year when the financial statement comes due, it ain't about the money but in the past couple of weeks I've gotten multiple complaints from members, decent guys good solid members, complaining that multiple posts have been deleted. One guy says he gets suspended and doesn't really know why. I haven't deleted anybody's posts that I haven't suspended anybody. I don't I don't think Larry even comes over here anymore so I wonder if it's Woody? I don't see why you would bother with it Tia. Anybody have a guess?
WSS
The deleted posts issue I believe is a Board/Software issue.
I've noticed this occurs on my super thread when a new page starts that the last posts on the previous thread start disappearing up to a point.
After several posts on the new page, the posts on the previous page start reappearing.
Now as for the instance where my entire thread disappeared, I have no idea what happened there, but would not be surprised to see it related to the above issue.
Memory, Drive space or Software issue ?
Who knows.
No one talking about this impossible catch ?
Freakin' unbelievable . . . guy's a 1st Rounder right now.
Not the first time I've seen him make World Class receptions . . .
Tate's amazing as well (coming out this year I believe).
For those in other areas :
Cleveland making a fairly exclusive Tour Club . . .
Was familiar with Rich Derringer, wasn't aware that he was from Ohio . . .
God speed . . .
This one came out last week.
Non trivial stuff.
Not really FB, but still OSU FB . . .
Not really a Band fan, but still pretty impressive.
Some of the hype about how fast this seems to be ramping up.
I can attest to seeing this behavior in several of the queries I've made.
I've also seen it suggest additional info to add to queries as it evaluates so that it can give better / more accurate answers.
For some queries on programming, I've had it add several suggestions for additional features and some modules to link and how to set them up for more functionality.
Not saying it's perfect, but that may just be the way the query was structured.
Pretty impressive though so far.
Could be scary too (Matrix / Terminator).
There have been about five new AI models from different companies come out in the last week.
I saw one report where someone had the AI rewrite a plugin it used and it doubled the performance for it.
I've not seen anything like that, though I'm not that deeply into it yet, nor sure if I will be.
Not sure if this has been in the MSM, but this is really big deal.
Deepseek-r1 was just released to the public late last week.
It's blown up since then, I've seen all kinds of positive posts about it.
Got me curious, as this one you can set up to run locally.
I set up a VM (lowers performance) on an external backup drive (even more performance degradation).
I did it this way just to have more isolation that won't impact my Computer while I'm doing other things while it runs in the background.
There are currently 7 different data models available from 1.1 GB up to 404 GB, most are "distilled" from the original, so there will be some accuracy issues due to that.
I'm fooling around with the 4.7 GB and 9.0 GB models, and while being slowed due how I set things up, it's pretty interesting.
I can easily see how this could be an assistive program for many things, from research to programming.
Only FB note I've dropped in the last several years - and only full game I've watched in that time.
QB to me is still questionable . . . too many INT's, even thought Team may overcome that.
D . . . damn ugly in the first Half for a supposedly Championship challenging Team in the First Half.
D . . . pretty much shut things down second Half - this is what you want too see, but has always been a concern to me over the last several years (D too soft).
This may also answer some questioning the Score of this game . . . OSU could have easily been in the 50+ points in this game (for those that didn't watch), even though the D started really slow.
There was just no need to put up that many points in this game . . . even though they could have easily done so.
No need to show future opponents your O capabilities . . .
Had to add those notes, as the only reason I've posted here is the Brown to Smith play at the ending of the 2Q.
Damn . . . that is the only play I've had me come out of my seat in I don't know how many years (NFL included) . . .
More I could say on this . . . but for now, let it go at this . . .
Please say it ain't so :

Crazy World, huh cal ?
Wish I was wrong, but it's looking worse than I was thinking - and it's coming dang fast.
May have some follow up on my other thread, as others may want the Memory jog.
The Circus is in session.
I found a real pretty rounded multilayered sedimentary rock in the middle of the upper Colorado River which is only about 6-8 inches deep in clear fresh water and maybe 15 ft. across. Rock appears to have been rolling quite a while since it was like an oblong smooth baseball. But about 20 layers of about 1/8 inch or so each. Made the 8 mile RT hike well worth it.
Might be worth a picture
If it was round, I might wonder if it was a Geode, don't know if they're found in more oval/oblong shapes though.