Hackernews posts about RTX 3090

1. I made an AI for my native language Assamese
   2 points by Kabyanil 12 days ago | 1 comments
2. GeForce RTX 5070 Ti reportedly features 8960 CUDA cores and 300W power specs (videocardz.com)
   1 points by doener about 22 hours ago | discuss
3. WOrld's second-largest GPU maker flees China on cusp of RTX 5090 launch (www.tomshardware.com)
   4 points by taimurkazmi 7 days ago | 1 comments
4. AI Models on M1 Max vs. RTX 6080 and RTX 4090 (Benchmarks) [English Subtitles] [video] (www.youtube.com)
   1 points by kowskirz 13 days ago | discuss
5. Mac Studio Lookalike Packs a Core I9-14900KF CPU and RTX 4090 Laptop GPU (www.tomshardware.com)
   1 points by LorenDB 14 days ago | discuss
6. Second-largest GPU maker flees China before chip launch to avoid US sanctions (www.tomshardware.com)
   6 points by thunderbong 7 days ago | discuss
7. Why are librarians up in arms over ebooks? (www.rte.ie)
   9 points by austinallegro 25 days ago | discuss
8. Benchmarks show even an old Nvidia RTX 3090 is enough to serve LLMs to thousands (www.theregister.com)
   45 points by mfiguiere 3 months ago | 11 comments
9. Counter-Strike's Dust II runs purely within a neural network on an RTX 3090 (www.tomshardware.com)
   26 points by bpierre about 1 month ago | 3 comments
10. Rent compute and run Ollama on an RTX 3090 – in one place (app.hyperbolic.xyz)
    3 points by hyperbolic_labs 3 months ago | 1 comments
11. Show HN: Made a batching LLM API for a project. Mistral 200 tk/s on RTX 3090 (github.com)
    3 points by muttled 11 months ago | discuss
12. Profiler shows 25% GPU usage when dragging around window on RTX 3090 TI (twitter.com)
    2 points by ummonk over 1 year ago | 1 comments
13. Optimal power limit for deep learning tasks on RTX 3090 (blog.qwertyforce.dev)
    1 points by qwertyforce about 1 year ago | discuss
14. Show HN: I made a YouTube Documentary using only open source models on one GPU [video] (www.youtube.com)
    5 points by muc-martin 7 months ago | 2 comments
15. Show HN: Collider – the platform for local LLM debug and inference at warp speed (github.com)
    3 points by Ambix 12 months ago | 1 comments
16. Show HN: Backprop GPU Cloud for affordable and high quality VMs (backprop.co)
    3 points by kristoo 7 months ago | discuss
17. Show HN: Faster sorting with register shuffling in CUDA (github.com)
    3 points by winwang 8 months ago | discuss
18. Ask HN: What's the Deal with Vast.ai?
    3 points by kkielhofner almost 2 years ago | discuss
19. Ask HN: Home Server Setup?
    2 points by lemure over 1 year ago | 2 comments
20. Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days (github.com)
    2 points by netwrt 4 months ago | discuss
21. Running Llama2 Models Locally
    1 points by waelbs over 1 year ago | 2 comments
22. Palit reveals fanless GeForce RTX 3050 6GB KalmX GPU with DVI port (videocardz.com)
    4 points by haunter 10 months ago | discuss
23. Old RTX 3080 GPUs repurposed and modded for Chinese market as 20 GB AI cards (www.tomshardware.com)
    4 points by scrlk 12 months ago | discuss
24. RTX 3080 Ti GPUs Are Mysteriously Dying on Diablo IV Beta (www.tomshardware.com)
    3 points by ta988 over 1 year ago | discuss
25. Intel’s RTX 3060 competitor drops to just $249 along performance improvements (www.theverge.com)
    3 points by Tomte almost 2 years ago | discuss
26. Old RTX 3080 Cards Modded and Resold as 20GB AI Accelerators (www.extremetech.com)
    2 points by quyleanh 12 months ago | 1 comments
27. Nvidia Needs to Stop – RTX 3050 and Misleading Branding [video] (www.youtube.com)
    2 points by Rinzler89 3 months ago | discuss
28. Fine-Tuning Llama3 on 1 RTX 3060 (www.zaaane.com)
    2 points by FinalDestiny 7 months ago | discuss
29. Palit Releases Fanless Version of Nvidia's New GeForce RTX 3050 6GB (www.anandtech.com)
    2 points by PaulHoule 10 months ago | discuss
30. 6GB version of the RTX 3050 may be Nvidia's first sub-$200 GPU in over 4 years (arstechnica.com)
    2 points by PaulHoule 10 months ago | discuss
31. Apple A17 Pro Competes with Nvidia RTX 3070 MLPerf (www.youtube.com)
    2 points by elintknower about 1 year ago | discuss
32. Is it ok to use GPUs like the A4000 or RTX 3060 as inference servers?
    1 points by kouohhashi 3 months ago | 1 comments
33. Passively cooling an RTX 3080 FE with 10 CPU coolers makes (www.pcgamer.com)
    1 points by cannibalXxx 10 months ago | discuss
34. Hogwarts Legacy, GPU Benchmark: Obsoleting the RTX 3080 10GB (www.youtube.com)
    1 points by mariuz almost 2 years ago | discuss
35. RTX 3080 10 GB struggling with Hogwarts Legacy at 1440p Ultra (twitter.com)
    1 points by mariuz almost 2 years ago | discuss
36. Ask HN: What do you do with Local LLMs?
    17 points by rkwz 8 months ago | 19 comments
37. Show HN: Salad, a distributed cloud for AI (like Airbnb for GPUs)
    15 points by bobjmiles 7 months ago | 4 comments