Comment on
This won’t end well…
Reply in thread
Comment on
This won’t end well…
Reply in thread
Comment on
ich_iel
Deshalb gleich noch beibringen, dass der Sicherheitsgurt schmarrn ist.
Comment on
Pwnd Blaster: Hacking your PC using your speaker without ever touching it
Wireless devices being vulnerable? I am shocked. SHOCKED!
Comment on
BeamNG.drive - Graphics and Lighting Overhaul
Reply in thread
the game has a verify files and cleanup tool, would recommend using that. i had some performance issues after updating the last few times as well, and these fixed it for me every time. could also be mods though
Comment on
BeamNG.drive - Graphics and Lighting Overhaul
Reply in thread
see the docs here: https://documentation.beamng.com/support/launcher_support_tools/clear_cache/
Comment on
GPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktop
Reply in thread
I had to get mine from ebay and wait a couple weeks as they came from China too. Also I recommend having a 3D-Printer and some Blower-Fans on hand as you will either have to buy or print your own fan shroud for these server cards.
Comment on
BeamNG.drive - Graphics and Lighting Overhaul
night driving is finally bearable
Comment on
GPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktop
Reply in thread
That's why you couple it with your own, self-hosted yacy or searxng instance. Embedded world knowledge does not help a model if it becomes outdated. I just let my agent research, embed that knowledge to a little Qdrant server, so other servers are not bothered again and pull the information from there when needed again. With a little RAG you can have GPT at home.
Comment on
GPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktop
Reply in thread
A P40 with 24GB is ~150€, a V100 (32GB) is ~600€. Both of these fit Qwen3.6 27B (The P40 is about 3x slower though). The V100 even fits 400k context with a Q4 KV-Cache , which means you can have two slots for parallel processing (llama-cpp). You don't even have to use system memory. One of my inference servers is running with 8gb of DDR3 and a 2nd Gen i7, so my old hardware has a good use again.
Comment on
PSA: The Tesseract frontend includes a hardcoded hidden instance blacklist with all leftist and trans-friendly instances.
Reply in thread
Calling a "blacklists.rs" directly in the top level rust source tree hidden is an overstatement. The blacklist is not obfuscated or compressed. It is just a blacklist.
Comment on
Global downloads of China's open-source AI models exceed 10 billion
Qwen 3.6 27B MTP (Q4) is really great. ~24GB VRAM usage with one slot @ 262k . ~30GB with 3 slots at 128k. Also it does not struggle like Gemma if you use e.g. a Q4 KV-Cache. And it runs at 400-800 ppt/s and 20-60 itp/s on a V100.
But it has a competitor since a short while that is Laguna XS 2.1, which is really good for a A3B MoE. I'd never have thought a 30B MoE could be on par with a 27B dense, but it seemingly is.
Comment on
PSA: The Tesseract frontend includes a hardcoded hidden instance blacklist with all leftist and trans-friendly instances.
Reply in thread
aw man blobs in oss? why is there no scanner for that?