Risse
Joined 15 years ago
Karma
450
Submissions
153
Member since
May 3
[ my public key: https://keybase.io/risse; my proof: https://keybase.io/risse/sigs/4KKaaLD3dBn7GUVpeIerDJXeMm3Mmk0jAY6iS73ll9Q ]
View on Hacker NewsRecent submissions
Comment · 5 days ago
24 GB 3090 user here. What is the best model for coding you have used? Qwen3.8 27B?
Comment · 12 days ago
Same thing here in Finland, our website on WP Engine has been down for at least an hour now.
Comment · 1 month ago
Depends on what you consider to "usefully run LLMs".
Earlier this year, I bought a mini pc from Aliexpress, specs are roughly Ryzen H255, 24GB LPDDR5, 1TB SSD. This was around 350€ including VAT, customs, shipping etc. I would personally consider this somewhat of a lowest class of useful LLM box. It can run 8B models well, up to somewhere around 24B. I currently run Gemma 4 26B A4B Q5 on it, with MTP, and it is quite slow, but smaller models would run okay on it.
Comment · 4 months ago
Somewhat of a verification, here's Mullvad's response to the post on Mastodon: https://mastodon.online/@mullvadnet/116822244689326681
Comment · 4 months ago
They might be having some capacity issues, it was 404 for me for a while but now it's back.
Archive: https://web.archive.org/web/20260629105534/https://det.socia...