Hacker News: SlavikCA

New comment by SlavikCA in "Show HN: Claude Code vs. Codex Global Usage Leaderboard"

SlavikCA — Fri, 15 May 2026 19:59:47 +0000

where that usage data coming from?

New comment by SlavikCA in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

SlavikCA — Wed, 22 Apr 2026 19:42:54 +0000

There is no standard.

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

New comment by SlavikCA in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

SlavikCA — Wed, 22 Apr 2026 19:25:04 +0000

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/...

New comment by SlavikCA in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

SlavikCA — Thu, 16 Apr 2026 17:50:18 +0000

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.

New comment by SlavikCA in "Darkbloom – Private inference on idle Macs"

SlavikCA — Thu, 16 Apr 2026 14:57:24 +0000

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

New comment by SlavikCA in "Professional video editing, right in the browser with WebGPU and WASM"

SlavikCA — Sun, 22 Mar 2026 00:33:58 +0000

Thank you. Just tried it.

UI is rather confusing.

New comment by SlavikCA in "Professional video editing, right in the browser with WebGPU and WASM"

SlavikCA — Sat, 21 Mar 2026 22:56:34 +0000

Great project!

Is there similar project for image editing?

Just basic features:

- cropping

- rotating

- brightness & contrast

New comment by SlavikCA in "Anthropic announces proof of distillation at scale by MiniMax, DeepSeek,Moonshot"

SlavikCA — Mon, 23 Feb 2026 19:16:13 +0000

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.

New comment by SlavikCA in "Court orders restart of all US offshore wind power construction"

SlavikCA — Tue, 03 Feb 2026 05:39:27 +0000

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.

New comment by SlavikCA in "Dealing with abandonware (2024)"

SlavikCA — Mon, 05 Jan 2026 23:14:44 +0000

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

New comment by SlavikCA in "MiniMax M2.1"

SlavikCA — Tue, 23 Dec 2025 17:07:58 +0000

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)

New comment by SlavikCA in "Show HN: Network Monitor – a GUI to spot anomalous connections on your Linux"

SlavikCA — Sat, 29 Nov 2025 18:43:13 +0000

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

New comment by SlavikCA in "Proxmox virtual environment 9.1 available"

SlavikCA — Wed, 19 Nov 2025 16:25:03 +0000

Looks like Incus has no GUI?

Proxmox has nice web GUI

New comment by SlavikCA in "Kubernetes Ingress Nginx is retiring"

SlavikCA — Fri, 14 Nov 2025 03:24:03 +0000

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?

New comment by SlavikCA in "Hard drives on backorder for two years as AI data centers trigger HDD shortage"

SlavikCA — Wed, 12 Nov 2025 19:23:09 +0000

And there is no profit, too.

New comment by SlavikCA in "ChatGPT terms disallow its use in providing legal and medical advice to others"

SlavikCA — Thu, 06 Nov 2025 00:12:45 +0000

Google released MedGemma model: "optimized for medical text and image comprehension".

I use it. Found it to be helpful.

New comment by SlavikCA in "Preventing Kubernetes from pulling the pause image from the internet"

SlavikCA — Wed, 05 Nov 2025 18:36:15 +0000

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.

New comment by SlavikCA in "Preventing Kubernetes from pulling the pause image from the internet"

SlavikCA — Wed, 05 Nov 2025 05:07:50 +0000

I'm running k3s at home on single node with local storage. Few blogs, forum, minIO.

Very easy, reliable.

Without k3s I would have use Docker, but k3s really adds important features: easier to manage network, more declarative configuration, bundled Traefik...

So, I'm convinced that quite a few people can happily and efficiently use k8s.

In the past I used other k8s distro (Harvester) which was much more complicated to use and fragile to maintain.

New comment by SlavikCA in "Proxmox Virtual Environment 9.0 with Debian 13 released"

SlavikCA — Tue, 05 Aug 2025 16:10:25 +0000

Proxmox has built-in support for CEPH, which is promoted as VMFS equivalent.

I don't have much experience with them, so can't tell if it's really on the same level.

New comment by SlavikCA in "ChatGPT agent: bridging research and action"

SlavikCA — Thu, 17 Jul 2025 17:43:16 +0000

That is the problem. LLMs can't be trusted.

I was searching on HuggingFace for the model which can fit on my system RAM + VRAM. And the way HuggingFace shows the models - bunch of files, showing size for each file, but doesn't show the total. I copy-pasted that page to LLM and asked to count the total. Some of LLMs counted correctly, and some - confidently gave me totally wrong number.

And that's not that complicated question.