Viewing profile — ColonelPhantom

Or HOGS? HTMX-OS-Go-Sqlite. While having "OS" in there is kind of redundant, it does make for a nice and general acronym.

Which model class requires an 80 GB VRAM GPU? From my perspective, popular models seem to be either in the ~30B range (Qwen3.6, Gemma 4), while the larger models (MiniMax, MiMo, St…

> the most likely experts Is that how MoEs work? I though that an important constraint for MoEs is that experts need to be uniformly used to make sure they can be used effectively.…

Deepseek V4 Flash still has 13B active params though? That is about half as many as Qwen3.6-27B (and much more than Qwen3.6-35B-A3B). Given that RAM (even on a base M4 or 'regular'…

Carp is memory safe via linear types + references, similar to Rust, so I would not describe it as C-like but rather Rust-like.

But what _is_ a "Text User Interface"? Google Images just returns what is being discussed here: "GUIs" that run in some kind of text mode. And to me, that's also what a TUI is. A m…

You mentioned Strix Halo, which also has off-die memory. Strix Halo does have a real advantage from its wider memory bus (four channels for 256 bit instead of 128 bit), but Strix P…

Hilariously, those AMD chips are way behind the Intels in terms of memory. First off, I believe that Intel has its memory far more "unified". AMD typically has a stricter VRAM/RAM …

Nvidia Turing (RTX 20) definitely marked a major shift IMO. - It was the first card to enable real-time ray-traced effects. - Mesh shaders are a significant overhaul of the geometr…

838 seems to be the real INT8 TOPS number for the 5090; going from 800 to 3400 takes an x2 speedup for sparsity (so skipping ops) and another x2 speedup for FP4 over INT8. So it's …

Aren't Intel Xeon Rapids and Intel Xeon Forest just different target markets? Rapids has fewer but faster cores in general, and more special-purpose accelerators (e.g. AMX, QAT), w…

Very cool! I am wondering one thing: how fast is it? Much of the "secret sauce" of the Voodoo is its high speed: a first-gen Verite or (God forbid) any ViRGE takes many more cycles…

GPT-OSS is tailored to be extremely memory efficient. Not only is it natively using the 4.25 bit per token MXFP4 format, but it also uses sliding window attention for half of its l…

Interesting; I was not aware of those "universal synthetics" but they make sense: a stronger reasoning base would make modeling tasks easier. Thanks for the link! Again, though, if…

If generating synthetic data is such a great way to improve performance, why would it not be applied to the slowrun? Especially for the unlimited compute track, you should have ple…

I like the idea of LLM-calling as an automation-friendly CLI tool! However, putting all my agents in ~/.config feels antithetical to this. My Bash scripts do not live there either,…

Interesting read! One remark though: I'm not too familiar with the architecture of a Google TPU, but comparing the TPU's VMEM with Nvidia's shared memory feels wrong to me. Looking…

The reason for that is that most memory bandwidth bumps come with new memory generations. For example an early DDR4 platform (e.g. Intel Skylake/Core iX-6000) and a late one (e.g. …

It's not just Qwen; we also recently had GLM-4.7-Flash in the same roughly 30B-A3 range. Seems to me like there's no shortage of competition for good old GPT-OSS 20B (not just Qwen…

> Meanwhile, European makers are stuck not knowing what to do, make Americans happy or compete with the Chinese. Huh? This comment sounds extremely America-centric to me. Porsche s…

Each layer of the LM is also at most 16 KiB, so if you want to minimize bank switching, I think making sure each layer is in one bank would be enough? Bank switching shouldn't give…

Touchegg kinda sucks (gestures are not 1:1 but rather just "triggered"), and you also don't need it. KDE and Gnome (as well as some WMs like Niri) have native touchpad gesture supp…

I have no idea what you are saying (with "is"??), but I don't think this is true: KDE Dolphin is very full-featured and runs natively on Wayland.

That's fair! I believe that window positioning also works on XWayland, though, so running your file manager that way should still work with the rest of the system being Wayland (an…