Hackernews posts about RTX 3090

1. 70M vectors searched in 48ms on a single consumer GPU –results you won't believe
   1 points by EffCompute 23 days ago | 4 comments
2. AluminatiAI – per-job GPU cost tracking (Nvidia-smi shows watts, not dollars)
   1 points by AluminatiAi 29 days ago | discuss
3. Tell HN: Llamacpp now supports unified system RAM offloading on Linux
   6 points by dabockster 14 days ago | discuss
4. Testing Nvidia's FP4: Running 70B LLMs on a Single RTX 5090 with Real Benchmarks (ai.gopubby.com)
   2 points by Aedelon 28 days ago | discuss
5. M5 Max MacBook Pro beats Nvidia RTX 5090 laptops at Blender 5.1 rendering (opendata.blender.org)
   1 points by ykl 19 days ago | 1 comments
6. Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs (dnhkng.github.io)
   495 points by dnhkng 29 days ago | 126 comments
7. I'm 11 and trained a custom MoE LLM for $1
   4 points by Hey1-Arthur 17 days ago | discuss
8. Show HN: NVFP4 on Desktop Blackwell – 122B MoE on a Single RTX PRO 6000 31 tok/s
   2 points by jcartu 30 days ago | discuss
9. Show HN: DAAO – Deploy AI agents to your servers via Zero-Trust tunnels (github.com)
   1 points by dan3093 25 days ago | discuss
10. Show HN: Turkish Sieve Engine – Full Prime Statistics Up to 10^14 and V2 Preview (github.com)
    1 points by bilgisoft 26 days ago | discuss
11. I fixed a segfault in Triton that broke every RTX 5070/5080/5090 (github.com)
    1 points by pat90000 22 days ago | discuss
12. Show HN: ADS-B Scope – Portable ADS-B and mesh radio on a LilyGo T-Display-P4 (adsb-scope.offx1.com)
    3 points by johnstockdale 14 days ago | discuss
13. LLM from scratch, part 28 – training a base model from scratch on an RTX 3090 (www.gilesthomas.com)
    540 points by gpjt 4 months ago | 121 comments
14. Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU (github.com)
    395 points by xaskasdf about 2 months ago | 101 comments
15. Benchmarks show even an old Nvidia RTX 3090 is enough to serve LLMs to thousands (www.theregister.com)
    45 points by mfiguiere over 1 year ago | 11 comments
16. Counter-Strike's Dust II runs purely within a neural network on an RTX 3090 (www.tomshardware.com)
    26 points by bpierre over 1 year ago | 3 comments
17. Dual RTX 5060 Ti 16GB vs. RTX 3090 for Local LLMs (www.hardware-corner.net)
    14 points by pietrushnic 10 months ago | 5 comments
18. Upgrading Fans with a Custom Shroud on a RTX3090 – Goodbye Fan Noise (boilingsteam.com)
    3 points by ekianjo 5 months ago | 1 comments
19. Rent compute and run Ollama on an RTX 3090 – in one place (app.hyperbolic.xyz)
    3 points by hyperbolic_labs over 1 year ago | 1 comments
20. Upgrading Fans with a Custom Shroud on a RTX3090 For A Silent Experience (boilingsteam.com)
    3 points by ekianjo 5 months ago | discuss
21. Fine-Tuning Nvidia's GR00T 2B Robotic Model on a RTX 3090 (twitter.com)
    3 points by nprobably about 1 year ago | discuss
22. Show HN: Federation of robots collaboratively train an object manipulation model (github.com)
    7 points by jafermarq about 1 year ago | discuss
23. Show HN: I made a YouTube Documentary using only open source models on one GPU [video] (www.youtube.com)
    5 points by muc-martin almost 2 years ago | 2 comments
24. Show HN: ZigNet: How I Built an MCP Server for Zig in 1.5 Days (fulgidus.github.io)
    4 points by Fulgidus 5 months ago | discuss
25. Show HN: Backprop GPU Cloud for affordable and high quality VMs (backprop.co)
    3 points by kristoo almost 2 years ago | discuss
26. Show HN: Accidentally built churn detection AI (I don't code) (github.com)
    2 points by willster787 8 months ago | 2 comments
27. Show HN: kulyk-uk-en and kulyk-en-uk (huggingface.co)
    2 points by yehors 9 months ago | 1 comments
28. Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days (github.com)
    2 points by netwrt over 1 year ago | discuss
29. Show HN: Localvoxtral – Local real-time dictation on macOS with streaming STT (github.com)
    1 points by T0mSIlver about 1 month ago | 2 comments
30. Show HN: I over-engineered a home security camera that uses an LLM and talks (github.com)
    1 points by thecal about 1 month ago | discuss
31. Show HN: Luna Agent – Custom AI agent in ~2300 lines of Python, no frameworks (nonatofabio.github.io)
    1 points by nonatofabio about 1 month ago | discuss
32. Show HN: QLoRA fine-tuning in .zse INT4 format by ZSE
    1 points by zyoralabs about 1 month ago | discuss
33. Show HN: GLM-Image Online – 16B AR+Diffusion model for accurate text (glmimage.online)
    1 points by hugh1st 3 months ago | discuss
34. 48GB RTX 8000 vs. 3090s for Local LLMs (www.hardware-corner.net)
    5 points by pietrushnic 10 months ago | discuss
35. Show HN: Local task classifier and dispatcher on RTX 3080 (github.com)
    26 points by Shubham_Amb 2 months ago | 2 comments
36. Running Qwen3:30B MoE on an RTX 3070 laptop with Ollama (blog.kekepower.com)
    18 points by kekePower 10 months ago | 1 comments
37. Is the Nvidia RTX 3060 the best value for entry level local AI? (aiflux.substack.com)
    3 points by ericdotlee 7 months ago | 2 comments
38. Memtest Vulkan v0.5.0 Benchmark on RTX 3070 Laptop GPU (blog.axiomgaming.net)
    2 points by Blake_Welsh 8 months ago | 1 comments
39. Nvidia Needs to Stop – RTX 3050 and Misleading Branding [video] (www.youtube.com)
    2 points by Rinzler89 over 1 year ago | discuss
40. Fine-Tuning Llama3 on 1 RTX 3060 (www.zaaane.com)
    2 points by FinalDestiny almost 2 years ago | discuss
41. Nvidia rumored to bring GeForce RTX 3060 production back this quarter (videocardz.com)
    1 points by alecco 3 months ago | 1 comments
42. Is it ok to use GPUs like the A4000 or RTX 3060 as inference servers?
    1 points by kouohhashi over 1 year ago | 1 comments