I'm getting 30 t/s on RTX 4090D (using 42 out of 48GB VRAM) with UD-Q6_K_XL

https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/discussions/...

I thought Q4_K_M is the standard. Why did you choose the 6-bit variant? Does it generate better input?

There is no standard.

The higher quantization - the better results, but more memory is needed. Q8 is the best.

FP32 is best, although I wonder if there isn’t something better I don’t know about. Q8 is for the most part equal to FP16 in practical terms by being smart about what is quantized, but iirc always slower than FP16 and FP8.

I'm running it on my Intel Xeon W5 with 256GB of DDR5 and Nvidia 72GB VRAM. Paid $7-8k for this system. Probably cost twice as much now.

Using UD-IQ4_NL quants.

Getting 13 t/s. Using it with thinking disabled.

I get 20 t/s on the UD-Q6_K_XL quant, Radeon 6800 XT.

Please offer new clients try it: at least let us to send few requests in the chat.

Great project!

Is there similar project for image editing?

Just basic features:

- cropping

- rotating

- brightness & contrast

photopea?

Yeah, Photopea isn't exactly basic but it's great. If this became the Photopea equivalent for video that would be awesome.

Thank you. Just tried it.

UI is rather confusing.

It's a photoshop clone but if you have not used that before I can see how it might be a lot!

So, only Americans can use data against others?

By the way, I'm running 400B model on my computer with 72GB VRAM: Qwen3.5-397B-A17B-GGUF/UD-Q4_K_XL getting 13 t/s. Subjectively, I feel it's runs at the level of Anthropic Claude, just slower.

Question for you, that 13t/s, is that pretty solid even with high context/tokens?

I know Apple marketing says 'look at our 20t/s' but they sent less than 40 tokens.

256 GB of RAM?

Are you talking about Biden?

The Keystone XL pipeline had been partially constructed before President Biden revoked the permit on January 20, 2021 on his first day in office. About 300 miles had been completed when TC Energy officially abandoned the project.

They told us that with AI you can vibe-code anything now...

So, no need to make old program to work. Just write new one.

/sarcasm

Or you could have AI figure out how to crack it.

The HuggingFace link is published, but not working yet: https://huggingface.co/MiniMaxAI/MiniMax-M2.1

Looks like this is 10 billion activated parameters / 230 billion in total.

So, this is biggest open model, which can be run on your own host / own hardware with somewhat decent speed. I'm getting 16 t/s on my Intel Xeon W5-3425 / DDR5-4800 / RTX4090D-48GB

And looking at the benchmark scores - it's not that far from SOTA (matches or exceeds the performance of Claude Sonnet 4.5)

That screenshot / video on README page is mostly unreadable. Can't get anything out of it.

This app is clearly a demonstration of GTK4's light/dark transition animation. Looks like it works perfectly to me!

Same for me.

What info does it show more than a:

"netstat -tulpn"

Wrote myself a script years ago that basically loops netstat -tulpn watch like for the same purpose - just wondering if your tool shows me more than that.

modern graphical interface, for a start

I was asking which information it shows not what output it uses to display that information....

Come on, now. You can see that it supports today’s most critical feature: it has dark mode and light mode.

/s

If you live in the terminal it's all dark mode*

* unless you are one of those weirdo's who has a black on white terminal in which case you should be on a watch list (/s in case wasn't immediately obvious).

I've been there since the DOS days when it was all dark mode, green phosphor characters on a black CRT. I was there when amber monitors were the new thing. (I still love sunglasses with brown lenses.) And I watched the early Apple computers with graphics and black-characters-on-white display style that has been the rage ever since... well since the recent new thing being dark mode.

It reminds me of fashion trends, miniskirts then maxis, up and down past the knee like tides.

Fads, that's the word.

I am exactly that kind of weirdo, but then again I’ve been reading black on white books for my entire life and I never thought to complain about it.

Looks like Incus has no GUI?

Proxmox has nice web GUI

It has one[1] (optional). Proxmox has a shittier, but more featureful, web UI.

[1]: https://blog.simos.info/how-to-install-and-setup-the-incus-w...

i like the proxmox web ui.

also, looking at the link you posted, it looks like incus can only do like a fraction of what proxmox can do. is that the case or is that web ui a limiting factor?