Otternonsenz

Thank you for the recommendation, and so far, it has been working great (within reason, haha). It doesn’t kill my rig when thinking, but it definitely needs more training wheels to nudge it towards the goal.

It seemed to get the idea of my prompt to extend the footer info (I want it to show the model abilities like tool calling or reasoning where the context percent thing is), made a plan and wrote the file, but then got hung up on implementation because it couldn’t figure out how Pi renders that part of the UI in Powershell

So possibly trying a different terminal might help on that front, haha

Fully agreed, and my hope is as open models grow and change, that getting some amount of this working on Pro-sumer hardware will be more attainable.

But certainly seems like we are a few years away from that, sadly.

Am I also screwed in being able to train my own small model or adjust another one with such a non-workhorse PC?

Now that I’m dipping more into this space, am gonna see what I can upgrade with the motherboard I have, but RAM pricing as it is, I’ll need to be smart about when I upgrade.

I very much appreciate the frank response, as it makes me feel less defeated at knowing my understanding of how it should work is not the full issue, hahaha

Is there any hope for people that cant even run 27B parameters, Qwen3.6 or otherwise? Are there any quantized models that do well with tool calling at smaller parameter sizes?

I do not have a crazy rig, a modest gaming one at that, but in trying to understand more about agents and their capabilities, I am SOL with my 16 GB of RAM and 8GB of VRAM. I can get most small, non tool calling models to perform well, but I've had major issues with anything over 9B doing anything more than reasoning (egregiously slow at higher parameter counts).

And so far, I cant get even Pi to extend itself or do any meaningful work with any of the models I currently can get to run.

And for the curiosity of those who are running open models locally, are there any open models that offer anything even looking like parity with commercial coding offerings? Or is there still more time for that to surface?

To be fair, I believe this protocol existed before Google’s thing, if I remember right.

Honestly not expecting to see an answer to a question I had for myself and other residential appraisers who want to have our own AVMs to run thru, that we can develop ourselves!

Was at a conference last week where I was trying to figure out where to start with automated value models, and this is perfect.

Then this might serve as an interesting opportunity for you to sell leads or direct them towards the info you’re scraping from.

Tho if it works as free advertisement on either side, that’s a win-win.

Zillow, OpenDoor, Redfin, and Realtor.com all pay for API access to the largest Multiple Listing Systems (except for Realtor because they are the ones that are selling the access).

They then use their own “special” algorithms to give their price estimate based on “relevant” factors by what you are describing.

Your real issue is that the agents putting these homes on the market have a financial stake in it selling, and own copyright to all the pictures and descriptions of their listings. So you have more liability if you are scraping their info.

Another issue is who is the target audience for this? Most serious homebuyers are going to use an agent or a trusted partner for a transaction, and are not excited about compounding layers of hurdles to purchase a home

I am a residential real estate appraiser in the US and real estate technologist, which is why I bring up these points.

  Location: South West US
  Remote: Preferred 
  Willing to relocate: For the right company
  Technologies: PHP, XML, JavaScript, some Powershell
  Résumé/CV: Can supply Residential Appraisal License as needed
  Email: [email protected]

I’m not looking to be hired for any full time position, but rather to be a subject matter expert for those who are doing business in residential appraisal, the residential housing space, or require better understanding of the secondary mortgage market for their startup.

As one of few young people in my profession, there is much potential in making a fairly opaque industry better known, and I’ve seen very few of my older peers interested in sharing the knowledge we hold (which is also why it is so hard to get into this profession).

I work full time in my geographic area, but I am able to set my schedule to my liking, so if I am someone who seems worthwhile to talk with, don’t hesitate to reach out!

I am curious, with the way you are using “<1% are going to pay for music on here”, is that to be read as “no more than 1% are going to pay for music on here” or that “less than 1% are going to pay for music on here”?

Is your point that people aren’t willing to pay for things if they have a choice not to?

Or is it that independent artists should be grateful that people see their work at all and that “most” people will just think they are a grifting sociopath?

Not sure what your issue with my comment is, but I’m interested in what you meant, as I feel I’m missing context that only you have at the moment.

Because a person might be willing:

-to directly support artists with buying the albums or songs at full price, rather than letting Spotify barely pay artists anything for their music (especially independent ones without industry connections)

-knowing you own your library and that once you’ve purchased media, there is nothing to take it away other than the sands of time taking back its silicate

-one does not need unlimited access to songs they will never hear, especially when natural discoverability on Spotify is so so versus trawling through sites like Bandcamp, Earmilk, RCRDLBL (I know it doesn’t exist anymore), or other places where new artists show their work in a way that Spotify doesn’t provide