timmy777

Thanks for sharing. However, this missed being a good writeup due to lack of numbers and data.

I'll give a specific example in my feedback, You said:

``` so far, so good, I was able to play with PyTorch and run Qwen3.6 on llama.cpp with a large context window ```

But there are no numbers, results or output paste. Performance, or timings.

Anyone with ram can run these models, it will just be impracticably slow. The halo strix is for a descent performance, so you sharing numbers will be valuable here.

Do you mind sharing these? Thanks!

How do you prevent government (and other people who can access the data) from rewriting history?

Do you hash them in some sort of block chain?

The inability to rewrite history will be a fantastic gift to the world.

Beautiful article. Nice research

Keep in mind, a presentation (text, or otherwise) is an art. Culture, background, experiences and ideologies influences art.

... and to address your tone, did you know, you can give feedback with empathy?

Cool

Sorry, the internet is full of people with low empathy.

Mistakes on internet are corrected in very harsh ways, and many times rarely forgiven.

But hey, keep writing, keep learning, keep reflecting and taking feedbacks to improve. Everyone does this

After the rant, the very least you could do is to educate us about the tool that allows us view codegen and "layout".

>>> Very typical for today's world where javascript coder counts as software engineer.

Oh, hello software engineer from yesterday's world.

Awesome. But how is this different from dgraph?