Hackernews posts about an RTX 3090

  1. Extending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090 (www.gilesthomas.com)
    2 points by ibobev 6 days ago | discuss
  2. Extending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090 (www.gilesthomas.com)
    1 points by gpjt 6 days ago | discuss
  3. Show HN: Don't trust me bro: fixing GPT-OSS (3.49B tokens, 1k GPU hours, 1x3090) (github.com)
    2 points by iamskeole 16 days ago | discuss
  4. LLM from scratch, part 28 – training a base model from scratch on an RTX 3090 (www.gilesthomas.com)
    540 points by gpjt 10 months ago | 121 comments
  5. We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
    165 points by GreenGames 5 months ago | 52 comments
  6. Counter-Strike's Dust II runs purely within a neural network on an RTX 3090 (www.tomshardware.com)
    26 points by bpierre almost 2 years ago | 3 comments
  7. Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090 (www.gilesthomas.com)
    16 points by gpjt about 2 months ago | discuss
  8. Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090 (www.gilesthomas.com)
    1 points by ibobev about 2 months ago | discuss
  9. Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com)
    6 points by GreenGames 5 months ago | 1 comments
  10. Show HN: ZigNet: How I Built an MCP Server for Zig in 1.5 Days (fulgidus.github.io)
    4 points by Fulgidus 11 months ago | discuss
  11. Show HN: Accidentally built churn detection AI (I don't code) (github.com)
    2 points by willster787 about 1 year ago | 2 comments
  12. Show HN: Localvoxtral – Local real-time dictation on macOS with streaming STT (github.com)
    1 points by T0mSIlver 7 months ago | 2 comments
  13. Show HN: I over-engineered a home security camera that uses an LLM and talks (github.com)
    1 points by thecal 6 months ago | discuss
  14. Story of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090s
    8 points by yolo-auto 3 months ago | 3 comments
  15. Show HN: Federation of robots collaboratively train an object manipulation model (github.com)
    7 points by jafermarq over 1 year ago | discuss
  16. Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
    2 points by dnosoz 5 months ago | 4 comments
  17. Show HN: GLM-Image Online – 16B AR+Diffusion model for accurate text (glmimage.online)
    1 points by hugh1st 8 months ago | discuss
  18. Running Qwen3:30B MoE on an RTX 3070 laptop with Ollama (blog.kekepower.com)
    18 points by kekePower over 1 year ago | 1 comments
  19. Show HN: Building a local FIX protocol triage agent on an RTX 3070 (domgalati.substack.com)
    2 points by dgalati 5 months ago | discuss
  20. Show HN: I built a real-time OSINT dashboard pulling 15 live global feeds (github.com)
    312 points by vancecookcobxin 6 months ago | 123 comments
  21. Show HN: AgenticSeek – Self-hosted alternative to cloud-based AI tools (github.com)
    122 points by Fosowl over 1 year ago | 18 comments
  22. Show HN: Real-time 4D Julia set navigation via gamepad (banditcat.github.io)
    17 points by BanditCat 10 months ago | discuss
  23. Show HN: OpenCode Senses, An insanely fast and highly accurate vision plugin (github.com)
    8 points by itsmeadarsh about 1 month ago | 2 comments
  24. Ask HN: Is the antigravity web site high CPU on your OS?
    3 points by newsoftheday 9 months ago | 2 comments
  25. I made an AI for my native language Assamese
    2 points by Kabyanil almost 2 years ago | 1 comments
  26. Show HN: I Am 15 and Built a Dual Backend MLP from Scratch Using CUDA C++ (github.com)
    1 points by muchlakshay about 1 year ago | 2 comments
  27. Show HN: Tracking book mentions across podcast episodes
    1 points by steyeomans 9 months ago | discuss
  28. Show HN: Model-agnostic cognitive architecture for LLMs (github.com)
    6 points by HimTortons 10 months ago | discuss
  29. Show HN: Local task classifier and dispatcher on RTX 3080 (github.com)
    26 points by Shubham_Amb 7 months ago | 2 comments
  30. Father fixes dead RTX 3070 with a jerry-rigged capacitor from an old radio (www.tomshardware.com)
    2 points by speckx 2 months ago | discuss
  31. Tell HN: Llamacpp now supports unified system RAM offloading on Linux
    6 points by dabockster 6 months ago | discuss
  32. Show HN: I’ve made a real-time 3D fluid simulation in WebGPU (splash-fluid.netlify.app)
    2 points by matsuoka-601 over 1 year ago | 6 comments
  33. Show HN: Qantify – GPU-Accelerated Trading Library with Advanced Math and AutoML (github.com)
    1 points by Alradyin 10 months ago | discuss