Hackernews posts about RTX 3090

1. Fine-Tuning Nvidia's GR00T 2B Robotic Model on a RTX 3090 (twitter.com)
   3 points by nprobably 28 days ago | discuss
2. Show HN: I’ve made a real-time 3D fluid simulation in WebGPU (splash-fluid.netlify.app)
   2 points by matsuoka-601 29 days ago | 6 comments
3. Dual RTX 5090 Beats $25,000 H100 in Real-World LLM Performance (www.hardware-corner.net)
   29 points by mdp2021 20 days ago | 12 comments
4. Running Local LLMs? [Tenstorrent] 32GB Card Might Be Better Than Your RTX 5090 (www.hardware-corner.net)
   16 points by mdp2021 13 days ago | 6 comments
5. Ask HN: Why do people buy Nvidia RTX 5090 at x2 the MSRP?
   11 points by behnamoh 4 days ago | 10 comments
6. Custom GeForce RTX 4090 48GB (videocardz.com)
   10 points by doener 29 days ago | discuss
7. GPU Server with 8 RTX 4090 (a16z.com)
   5 points by m3at 16 days ago | 2 comments
8. Building an Efficient GPU Server with Nvidia GeForce RTX 4090s/5090s (a16z.com)
   5 points by walterbell 18 days ago | 2 comments
9. Building an Efficient GPU Server with Nvidia GeForce RTX 4090s/5090s (a16z.com)
   4 points by monkeydust 17 days ago | discuss
10. RTX 5090 Mobile: First LLM Benchmarks Are In (www.hardware-corner.net)
    3 points by mdp2021 24 days ago | discuss
11. Ask HN: "RTX 5090" or "DGX Spark"
    2 points by 9front about 15 hours ago | 1 comments
12. A16Z built a super-efficient AI GPU server from scratch with RTX 4090s (a16z.com)
    1 points by chadbennett 16 days ago | 1 comments
13. Benchmarks show even an old Nvidia RTX 3090 is enough to serve LLMs to thousands (www.theregister.com)
    45 points by mfiguiere 8 months ago | 11 comments
14. Counter-Strike's Dust II runs purely within a neural network on an RTX 3090 (www.tomshardware.com)
    26 points by bpierre 6 months ago | 3 comments
15. Rent compute and run Ollama on an RTX 3090 – in one place (app.hyperbolic.xyz)
    3 points by hyperbolic_labs 8 months ago | 1 comments
16. Show HN: Made a batching LLM API for a project. Mistral 200 tk/s on RTX 3090 (github.com)
    3 points by muttled over 1 year ago | discuss
17. Optimal power limit for deep learning tasks on RTX 3090 (blog.qwertyforce.dev)
    1 points by qwertyforce over 1 year ago | discuss
18. Show HN: Federation of robots collaboratively train an object manipulation model (github.com)
    7 points by jafermarq 3 months ago | discuss
19. Show HN: I made a YouTube Documentary using only open source models on one GPU [video] (www.youtube.com)
    5 points by muc-martin 12 months ago | 2 comments
20. Show HN: Collider – the platform for local LLM debug and inference at warp speed (github.com)
    3 points by Ambix over 1 year ago | 1 comments
21. Show HN: Backprop GPU Cloud for affordable and high quality VMs (backprop.co)
    3 points by kristoo about 1 year ago | discuss
22. Show HN: Faster sorting with register shuffling in CUDA (github.com)
    3 points by winwang about 1 year ago | discuss
23. Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days (github.com)
    2 points by netwrt 9 months ago | discuss
24. Running Llama2 Models Locally
    1 points by waelbs over 1 year ago | 2 comments
25. Palit reveals fanless GeForce RTX 3050 6GB KalmX GPU with DVI port (videocardz.com)
    4 points by haunter about 1 year ago | discuss
26. Old RTX 3080 GPUs repurposed and modded for Chinese market as 20 GB AI cards (www.tomshardware.com)
    4 points by scrlk over 1 year ago | discuss
27. Old RTX 3080 Cards Modded and Resold as 20GB AI Accelerators (www.extremetech.com)
    2 points by quyleanh over 1 year ago | 1 comments
28. Nvidia Needs to Stop – RTX 3050 and Misleading Branding [video] (www.youtube.com)
    2 points by Rinzler89 8 months ago | discuss
29. Fine-Tuning Llama3 on 1 RTX 3060 (www.zaaane.com)
    2 points by FinalDestiny 12 months ago | discuss
30. Palit Releases Fanless Version of Nvidia's New GeForce RTX 3050 6GB (www.anandtech.com)
    2 points by PaulHoule about 1 year ago | discuss
31. 6GB version of the RTX 3050 may be Nvidia's first sub-$200 GPU in over 4 years (arstechnica.com)
    2 points by PaulHoule about 1 year ago | discuss
32. Apple A17 Pro Competes with Nvidia RTX 3070 MLPerf (www.youtube.com)
    2 points by elintknower over 1 year ago | discuss
33. Is it ok to use GPUs like the A4000 or RTX 3060 as inference servers?
    1 points by kouohhashi 8 months ago | 1 comments
34. Passively cooling an RTX 3080 FE with 10 CPU coolers makes (www.pcgamer.com)
    1 points by cannibalXxx about 1 year ago | discuss
35. Ask HN: What do you do with Local LLMs?
    17 points by rkwz about 1 year ago | 19 comments
36. Show HN: Salad, a distributed cloud for AI (like Airbnb for GPUs)
    15 points by bobjmiles 12 months ago | 4 comments
37. Show HN: Like grep but for natural questions. Mixtral 8x7B – 28 tok/s on 8GB GPU (github.com)
    10 points by molli about 1 year ago | discuss
38. Show HN: Animating the World of Van Gogh with Stable Diffusion and AnimateDiff [video] (www.youtube.com)
    9 points by anonymousd3vil about 1 year ago | discuss
39. Ask HN: Recommended Gaming Laptop for Work?
    5 points by smusamashah over 1 year ago | 7 comments
40. Ask HN: What to do with a powerful PC if you don't play games?
    3 points by angryGhost almost 2 years ago | 4 comments
41. Ask HN: Looking for ML side project ideas
    2 points by Heidaradar about 1 year ago | 6 comments
42. I made an AI for my native language Assamese
    2 points by Kabyanil 5 months ago | 1 comments