Hackernews posts about RTX

RSS feed for RTX

Related:Nvidia

91
newRun Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sgithub.com
▲ 862snehesht 26h 💬 387
92
newQwen3.8-Flash-Next non-uniform quantization runs on 2 RTX3090shuggingface.co
▲ 9pfeifferj 20d 💬 2
93
newNvidia Launches RTX 5500 Pro Blackwell Desktop Edition with 84GB GDDR7 RAMwww.tomshardware.com
▲ 6bhouston 20d 💬 4
94
newBuying an RTX 5090? You Need to Promise You Won't Export It Firstwww.extremetech.com
▲ 5speckx 2d 💬 1
95
newTuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090sdoug.sh
▲ 5dougcalobrisi 20d 💬 1
96
newNvidia's RTX 5090 ($9,500) vanishes from online retail in the USwww.tomshardware.com
▲ 5speckx 20d 💬 1
97
newShow HN: Kairo – Fail-closed LLM inference routing from RTX 5090 measurementsgithub.com
▲ 5peter941221 21d discuss
98
newDeepSeek v4.1 Flash avg 102 tps on 4x RTX6000 pro max-q, 2.1x up from v4-flashforum.level1techs.com
▲ 4ambientlight 16d 💬 2
99
newShow HN: LingBot-World 2.0 (1.3B) running at 16 FPS on one RTX 5090github.com
▲ 4kaarelson 16d 💬 2
100
newUnattended 24hr Full-Stack Build: Qwen 3.8 27B on a Single RTX 5090github.com
▲ 4anglepoiselife 13d 💬 1
101
newAsus ProArt P16 Laptop (H7607, RTX Spark)www.asus.com
▲ 3peter_d_sherman 4d 💬 1
102
newNvidia Announces RTX Pro 5500 Blackwell Workstation Editionwww.nvidia.com
▲ 3jfaat 21d 💬 1
103
newI Built a System One Model on a RTX 3070twitter.com
▲ 3lafalce 15d discuss
104
newMicro Center requires RTX 5090 buyers to show ID and sign no-export declarationvideocardz.com
▲ 2haunter 24h 💬 1
105
newEnables Nvidia DLSS Frame Generation (DLSS-G) on RTX 30-series and RTX 20-seriesgithub.com
▲ 2metrofun 12d discuss
106
newMicrosoft Confirms October 7 Windows and Surface Event Featuring RTX Sparkwww.gadgetreview.com
▲ 2peter_d_sherman 16d discuss
107
newNvidia Unveils RTX Pro 5500 Blackwell Workstation Edition GPUwww.nvidia.com
▲ 2pelcg 20d discuss
108
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 2ibobev 24d discuss
109
newSingle-slot low-profile 75W RTX 3060 with no power connectors disappointswww.tomshardware.com
▲ 2sbulaev 28d discuss
110
newShow HN: 188M Hindi encoder, 28B tokens, 8K context, 1× RTX 4090github.com
▲ 2kkkamur 28d discuss
111
newAI Firms Are Reportedly Buying Nvidia RTX 5090 GPUs in Bulk for Server Usewww.techpowerup.com
▲ 1geoffbp 21d 💬 2
112
newQwen3.8-Flash-Next 177B running at 11–15 tok/s on 1 RTX 5070 12GB and 32GB RAMgithub.com
▲ 1maziianobeatz58 32h discuss
113
newBeacon: A prime-gap world record (merit 42.5192) on four RTX 5090 GPUszenodo.org
▲ 1mvojvoda 9d discuss
114
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 1gpjt 24d discuss
115
newShow HN: InstinctFlash – High-Performance Serving Runtime for Robotics Modelsgithub.com
▲ 27guanming0717 12d 💬 4
116
newShow HN: Plurnk (Yet *Another* AI Harness)github.com
▲ 1wikitopian 19d discuss
117
newMicro Center requires photo ID and signed no-export pledge to buy gaming GPUwww.tomshardware.com
▲ 9aillia 20h 💬 2
118
newNvidia Personal AI Router (Pair)www.nvidia.com
▲ 4florianherrengt 27d 💬 1
119
newHijacking the PS5's RTMP streamyashgarg.dev
▲ 295ibobev 6d 💬 92
120
newRTK reports token savings, but our cost benchmarks disagreequesma.com
▲ 170michalwarda 24d 💬 84

More stories →