Hackernews posts about RTX 3090

1. PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090 (github.com)
   3 points by GreenGames 22 days ago | 1 comments
2. Club-3090 Recipes for serving QWEN3.6 27B locally on RTX 3090s (github.com)
   1 points by lastdong 18 days ago | discuss
3. Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
   2 points by dnosoz 24 days ago | 4 comments
4. Enabling Resizable Bar on RTX 3080 Vbios via GitHub (github.com)
   7 points by linux_lorax 6 days ago | 5 comments
5. Fully-functional RTX 3070 16GB gets frankensteined into existence (www.tomshardware.com)
   2 points by Timofeibu 9 days ago | discuss
6. Show HN: Building a local FIX protocol triage agent on an RTX 3070 (domgalati.substack.com)
   2 points by dgalati 28 days ago | discuss
7. RTX 5090 and M4 MacBook Air: Can It Game? (scottjg.com)
   699 points by allenleee 9 days ago | 180 comments
8. RTX 5090 and M4 MacBook Air: Implementing PCI Passthrough for Gaming (scottjg.com)
   11 points by scottjg 18 days ago | discuss
9. Nvidia Preparing RTX 5090 Price Increase Due to Rising GDDR7 Memory Costs (mp1st.com)
   4 points by jeffufl 7 days ago | discuss
10. Q8 KV cache lets a 30B model fit 100K context on a 24 GB RTX 5090 (buraak.com)
    3 points by bozdemir 17 days ago | discuss
11. RTX 4090 sent for repair is a sophisticated fake with laser-etched VRAM and core (www.tomshardware.com)
    3 points by y1n0 26 days ago | discuss
12. Show HN: We dropped Go for Rust in our real-time telephony AI media plane
    3 points by bajpailabs 2 days ago | discuss
13. Show HN: We put ZK attribute proofs inside x402 payment headers
    2 points by aggre 25 days ago | 1 comments
14. LLM from scratch, part 28 – training a base model from scratch on an RTX 3090 (www.gilesthomas.com)
    540 points by gpjt 6 months ago | 121 comments
15. Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU (github.com)
    395 points by xaskasdf 3 months ago | 101 comments
16. We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
    165 points by GreenGames about 1 month ago | 52 comments
17. 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
18. 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
19. Dual RTX 5060 Ti 16GB vs. RTX 3090 for Local LLMs (www.hardware-corner.net)
    14 points by pietrushnic 12 months ago | 5 comments
20. Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com)
    6 points by GreenGames about 1 month ago | 1 comments
21. Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090 (github.com)
    5 points by thc1006 about 1 month ago | 2 comments
22. Upgrading Fans with a Custom Shroud on a RTX3090 – Goodbye Fan Noise (boilingsteam.com)
    3 points by ekianjo 6 months ago | 1 comments
23. Rent compute and run Ollama on an RTX 3090 – in one place (app.hyperbolic.xyz)
    3 points by hyperbolic_labs almost 2 years ago | 1 comments
24. I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090 (austinsnerdythings.com)
    3 points by auspiv about 1 month ago | discuss
25. Upgrading Fans with a Custom Shroud on a RTX3090 For A Silent Experience (boilingsteam.com)
    3 points by ekianjo 6 months ago | discuss
26. Fine-Tuning Nvidia's GR00T 2B Robotic Model on a RTX 3090 (twitter.com)
    3 points by nprobably about 1 year ago | discuss
27. Show HN: Federation of robots collaboratively train an object manipulation model (github.com)
    7 points by jafermarq over 1 year ago | discuss
28. Show HN: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant
    4 points by freakynit about 1 month ago | 2 comments
29. Show HN: ZigNet: How I Built an MCP Server for Zig in 1.5 Days (fulgidus.github.io)
    4 points by Fulgidus 7 months ago | discuss
30. Show HN: Accidentally built churn detection AI (I don't code) (github.com)
    2 points by willster787 9 months ago | 2 comments
31. Show HN: kulyk-uk-en and kulyk-en-uk (huggingface.co)
    2 points by yehors 10 months ago | 1 comments
32. Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days (github.com)
    2 points by netwrt almost 2 years ago | discuss
33. 70M vectors searched in 48ms on a single consumer GPU –results you won't believe
    1 points by EffCompute 2 months ago | 4 comments
34. Show HN: Localvoxtral – Local real-time dictation on macOS with streaming STT (github.com)
    1 points by T0mSIlver 3 months ago | 2 comments
35. AluminatiAI – per-job GPU cost tracking (Nvidia-smi shows watts, not dollars)
    1 points by AluminatiAi 2 months ago | discuss
36. Show HN: I over-engineered a home security camera that uses an LLM and talks (github.com)
    1 points by thecal 3 months ago | discuss
37. Show HN: Luna Agent – Custom AI agent in ~2300 lines of Python, no frameworks (nonatofabio.github.io)
    1 points by nonatofabio 3 months ago | discuss
38. Show HN: QLoRA fine-tuning in .zse INT4 format by ZSE
    1 points by zyoralabs 3 months ago | discuss
39. Show HN: GLM-Image Online – 16B AR+Diffusion model for accurate text (glmimage.online)
    1 points by hugh1st 4 months ago | discuss
40. 48GB RTX 8000 vs. 3090s for Local LLMs (www.hardware-corner.net)
    5 points by pietrushnic 11 months ago | discuss
41. Show HN: Local task classifier and dispatcher on RTX 3080 (github.com)
    26 points by Shubham_Amb 4 months ago | 2 comments
42. Running Qwen3:30B MoE on an RTX 3070 laptop with Ollama (blog.kekepower.com)
    18 points by kekePower 12 months ago | 1 comments
43. Is the Nvidia RTX 3060 the best value for entry level local AI? (aiflux.substack.com)
    3 points by ericdotlee 8 months ago | 2 comments