HackerTrans
TopNewTrendsCommentsPastAskShowJobs

SlavikCA

229 karmajoined 7 tahun yang lalu

comments

SlavikCA
·kemarin dulu·discuss
Does Android have this feature?
SlavikCA
·18 hari yang lalu·discuss
And with MTP (or other speculation techniques) you can ~double that.
SlavikCA
·22 hari yang lalu·discuss
dual CPU is bad idea for inference: single CPU works few times faster than dual because of NUMA limitations.
SlavikCA
·2 bulan yang lalu·discuss
where that usage data coming from?
SlavikCA
·3 bulan yang lalu·discuss
There is no standard.

The higher quantization - the better results, but more memory is needed. Q8 is the best.
SlavikCA
·3 bulan yang lalu·discuss
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/...
SlavikCA
·3 bulan yang lalu·discuss
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.
SlavikCA
·3 bulan yang lalu·discuss
Please offer new clients try it: at least let us to send few requests in the chat.
SlavikCA
·4 bulan yang lalu·discuss
Thank you. Just tried it.

UI is rather confusing.
SlavikCA
·4 bulan yang lalu·discuss
Great project!

Is there similar project for image editing?

Just basic features:

- cropping

- rotating

- brightness & contrast
SlavikCA
·5 bulan yang lalu·discuss
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.
SlavikCA
·5 bulan yang lalu·discuss
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.
SlavikCA
·6 bulan yang lalu·discuss
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
SlavikCA
·7 bulan yang lalu·discuss
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)
SlavikCA
·7 bulan yang lalu·discuss
That screenshot / video on README page is mostly unreadable. Can't get anything out of it.
SlavikCA
·8 bulan yang lalu·discuss
Looks like Incus has no GUI?

Proxmox has nice web GUI
SlavikCA
·8 bulan yang lalu·discuss
Reading few blogs and forums about it today - people talking about switching to Gateway API (from "legacy" Ingress).

And I do not understand it:

1. Ingress still works, it's not deprecated.

2. There a lot of controllers, which supports both: Gateway API and Ingress (for example Traefik)

So, how Ingress Nginx retiring related / affects switch to Gateway API?
SlavikCA
·8 bulan yang lalu·discuss
And there is no profit, too.
SlavikCA
·8 bulan yang lalu·discuss
Google released MedGemma model: "optimized for medical text and image comprehension".

I use it. Found it to be helpful.
SlavikCA
·8 bulan yang lalu·discuss
I tried Talos few month ago. Found it unstable and complicated; reported few bugs.

And because they are "immutable" - I found it's significantly more complicated to use with no tangible benefits. I do not want to learn and deal declarative machine configs, learn how to create custom images with GPU drivers...

Quite a few things which I get done on Ubuntu / Debian under 60 seconds - takes me half an hour to figure out with Talos.