Hey, Gabe Newell might be your man here. But it's not for profit.

https://luxurylaunches.com/transport/gabe-newell-explorer-ve...

https://www.forbes.com/sites/deajusufi/2026/06/13/gabe-newel...

For as long as I've known of Gabe from working in the game industry, I somehow always forget about his not-so-little hobby of being a sea-faring cyber pirate.

Similar recent posting with optimizations for older Xeon:

High-Performance AI on a Budget: Optimizing llama.cpp for Qwen3.5 Inference on a Dual-GPU HP Z440

https://news.ycombinator.com/item?id=47320244

Probably easier with Trellis 2 or Meshy.ai

In Germany it is possible to register an ENUM domain for a phone number. This provides a DNS mapping from the E164 number to DNS records, e.g. for IP phones, etc.

Decentralized and under user control, no shitty silos like FaceTime, WhatsApp.

ENUM stands for “Telephone Number Mapping.” It is essentially a bridge between the world of telecommunications and the Internet. With a single ENUM domain, you can combine all your contact options under your familiar phone number:

https://www.denic.de/en/products/enum-domains/

The main point of ENUM was compatibility with open SIP, unfortunately that never really happened and most SIP operators do not accept incoming calls from public internet (and do not route outgoing calls based on ENUM).

Sadly ENUM is dead or buried or both for many countries.

I saw this lets you do Fax over IP. Any other advantages or usecases?

I don't know if this gets much personal use, seems real cumbersome.

But this is of huge interest to carriers, since it allows them to skip the PSTN/peering cost when the callee endpoint is an IP phone.

There is private ENUM for carrier use I recall, not sure what the current status is, with LTE/VoLTE, RCS etc.pp.

http://dam3d3.free.fr/PFE/Pathfinder/GSMA_PathFinder_WebSite...

Here the list of countries that have ENUM delegated for their country code.

https://www.itu.int/en/ITU-T/inr/enum/Pages/delegations.aspx

Time travel.

The hierarchical geographical domains you are remembering must have been the 2000 '.geo' Top Level Domain (TLD) proposal from SRI. It didn't work out, but I remember thinking at the time that it was a cool idea.

It would have provided geographical information based on a domain encoded grid, not for human but machine consumption (e.g. acme.2e5n.10e30n.geo).

https://en.wikipedia.org/wiki/.geo

In a similar vein there is the 'e164.arpa' domain for mapping telephone numbers.

https://en.wikipedia.org/wiki/Telephone_number_mapping

One of the gems that a publicly funded broadcasting system gave us.

TPU architecture explained

https://news.ycombinator.com/item?id=47637597

A 11 year old dupe, I know. But first time I’ve seen it, and it just added to my admiration for him. And, it’s just as applicable today as it was 24 years ago!

https://news.ycombinator.com/item?id=7567159

Yes, they are listed on huggingface. The instruction trained models have an 'it' in their name.

https://huggingface.co/collections/unsloth/gemma-4

Edit: Sorry, I'm not sure if this is a quant, but it says 'finetuned' from the Google Gemma 4 parent snapshot. It's the same size as the UD 8-bit quant though.

Only the 'it' models seem to have quants. I was really hoping to try a base model.

Basic quantization is easy if you have enough RAM (not VRAM) to load the weights.

They explain it here:

https://unsloth.ai/docs/basics/unsloth-dynamic-2.0-ggufs

For the best quality reply, I used the Gemma-4 31B UD-Q8_K_XL quant with Unsloth Studio to summarize the URL with web search. It produced 4.9 tok/s (including web search) on an MacBook Pro M1 Max with 64GB.

Here an excerpt of it's own words:

Unsloth Dynamic 2.0 Quantization

Dynamic 2.0 is not just a "bit-reduction" but an intelligent, per-layer optimization strategy.

- Selective Layer Quantization: Instead of making every layer 4-bit, Dynamic 2.0 analyzes every single layer and selectively adjusts the quantization type. Some critical layers may be kept at higher precision, while less critical layers are compressed more.

- Model-Specific Tailoring: The quantization scheme is custom-built for each model. For example, the layers selected for quantization in Gemma 3 are completely different from those in Llama 4.

- High-Quality Calibration: They use a hand-curated calibration dataset of >1.5M tokens specifically designed to enhance conversational chat performance, rather than just optimizing for Wikipedia-style text.

- Architecture Agnostic: While previous versions were mostly effective for MoE (Mixture of Experts) models, Dynamic 2.0 works for all architectures (both MoE and non-MoE).