Hackernews posts about RTX

1. 01
   

   newRun Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sgithub.com

   ▲ 820snehesht22h💬 363savesaved
2. 02
   

   newQwen3.8-Flash-Next non-uniform quantization runs on 2 RTX3090shuggingface.co

   ▲ 9pfeifferj20d💬 2savesaved
3. 03
   

   newNvidia Launches RTX 5500 Pro Blackwell Desktop Edition with 84GB GDDR7 RAMwww.tomshardware.com

   ▲ 6bhouston20d💬 4savesaved
4. 04
   

   newBuying an RTX 5090? You Need to Promise You Won't Export It Firstwww.extremetech.com

   ▲ 5speckx2d💬 1savesaved
5. 05
   

   newTuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090sdoug.sh

   ▲ 5dougcalobrisi19d💬 1savesaved
6. 06
   

   newNvidia's RTX 5090 ($9,500) vanishes from online retail in the USwww.tomshardware.com

   ▲ 5speckx20d💬 1savesaved
7. 07
   

   newShow HN: Kairo – Fail-closed LLM inference routing from RTX 5090 measurementsgithub.com

   ▲ 5peter94122121ddiscusssavesaved
8. 08
   

   newDeepSeek v4.1 Flash avg 102 tps on 4x RTX6000 pro max-q, 2.1x up from v4-flashforum.level1techs.com

   ▲ 4ambientlight16d💬 2savesaved
9. 09
   

   newShow HN: LingBot-World 2.0 (1.3B) running at 16 FPS on one RTX 5090github.com

   ▲ 4kaarelson16d💬 2savesaved
10. 10
    

    newUnattended 24hr Full-Stack Build: Qwen 3.8 27B on a Single RTX 5090github.com

    ▲ 4anglepoiselife13d💬 1savesaved
11. 11
    

    newAsus ProArt P16 Laptop (H7607, RTX Spark)www.asus.com

    ▲ 3peter_d_sherman3d💬 1savesaved
12. 12
    

    newNvidia Announces RTX Pro 5500 Blackwell Workstation Editionwww.nvidia.com

    ▲ 3jfaat20d💬 1savesaved
13. 13
    

    newI Built a System One Model on a RTX 3070twitter.com

    ▲ 3lafalce15ddiscusssavesaved
14. 14
    

    newMicro Center requires RTX 5090 buyers to show ID and sign no-export declarationvideocardz.com

    ▲ 2haunter21h💬 1savesaved
15. 15
    

    newEnables Nvidia DLSS Frame Generation (DLSS-G) on RTX 30-series and RTX 20-seriesgithub.com

    ▲ 2metrofun12ddiscusssavesaved
16. 16
    

    newMicrosoft Confirms October 7 Windows and Surface Event Featuring RTX Sparkwww.gadgetreview.com

    ▲ 2peter_d_sherman16ddiscusssavesaved
17. 17
    

    newNvidia Unveils RTX Pro 5500 Blackwell Workstation Edition GPUwww.nvidia.com

    ▲ 2pelcg20ddiscusssavesaved
18. 18
    

    newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com

    ▲ 2ibobev24ddiscusssavesaved
19. 19
    

    newSingle-slot low-profile 75W RTX 3060 with no power connectors disappointswww.tomshardware.com

    ▲ 2sbulaev28ddiscusssavesaved
20. 20
    

    newShow HN: 188M Hindi encoder, 28B tokens, 8K context, 1× RTX 4090github.com

    ▲ 2kkkamur28ddiscusssavesaved
21. 21
    

    newAI Firms Are Reportedly Buying Nvidia RTX 5090 GPUs in Bulk for Server Usewww.techpowerup.com

    ▲ 1geoffbp21d💬 2savesaved
22. 22
    

    newQwen3.8-Flash-Next 177B running at 11–15 tok/s on 1 RTX 5070 12GB and 32GB RAMgithub.com

    ▲ 1maziianobeatz5828hdiscusssavesaved
23. 23
    

    newBeacon: A prime-gap world record (merit 42.5192) on four RTX 5090 GPUszenodo.org

    ▲ 1mvojvoda9ddiscusssavesaved
24. 24
    

    newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com

    ▲ 1gpjt24ddiscusssavesaved
25. 25
    

    newShow HN: InstinctFlash – High-Performance Serving Runtime for Robotics Modelsgithub.com

    ▲ 27guanming071712d💬 4savesaved
26. 26
    

    newShow HN: Plurnk (Yet *Another* AI Harness)github.com

    ▲ 1wikitopian19ddiscusssavesaved
27. 27
    

    newMicro Center requires photo ID and signed no-export pledge to buy gaming GPUwww.tomshardware.com

    ▲ 9aillia16h💬 2savesaved
28. 28
    

    newNvidia Personal AI Router (Pair)www.nvidia.com

    ▲ 4florianherrengt26d💬 1savesaved
29. 29
    

    newHijacking the PS5's RTMP streamyashgarg.dev

    ▲ 295ibobev6d💬 92savesaved
30. 30
    

    newRTK reports token savings, but our cost benchmarks disagreequesma.com

    ▲ 170michalwarda23d💬 84savesaved

· edit