Hackernews posts about RTX 3060

RTX 3060 is a graphics processing unit (GPU) designed by Nvidia for gaming and other compute-intensive tasks, particularly popular among cryptocurrency miners due to its high performance and relatively affordable price point.

RSS feed for RTX 3060

Related:Nvidia GeForce

01
newSingle-slot low-profile 75W RTX 3060 with no power connectors disappointswww.tomshardware.com
▲ 2sbulaev 27d discuss
02
newTuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090sdoug.sh
▲ 5dougcalobrisi 19d 💬 1
03
newI Built a System One Model on a RTX 3070twitter.com
▲ 3lafalce 14d discuss
04
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 2ibobev 23d discuss
05
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 1gpjt 24d discuss
06
newTell HN: I found 4 gaming PCs including GTX1080, GTX2070Super and 2 RTX3060's
▲ 5andrewstuart 634d discuss
07
newIs the Nvidia RTX 3060 the best value for entry level local AI?aiflux.substack.com
▲ 3ericdotlee 376d 💬 2
08
newNvidia RTX 3060 returns to retail 5 years after original launch, priced at $339www.tomshardware.com
▲ 2akyuu 85d discuss
09
newBalder v7 – 100% on SWE-bench Verified on a single RTX 3060
▲ 1BalderForseti 71d 💬 1
10
newNvidia rumored to bring GeForce RTX 3060 production back this quartervideocardz.com
▲ 1alecco 271d 💬 1
11
newShow HN: AgenticSeek – Self-hosted alternative to cloud-based AI toolsgithub.com
▲ 122Fosowl 526d 💬 18
12
newAsk HN: Nvidia GeForce RTX 5060 arrives May 19 at $299 revive PC builds?
▲ 10byte-bolter 514d 💬 12
13
newTell HN: Llamacpp now supports unified system RAM offloading on Linux
▲ 6dabockster 193d discuss
14
newShow HN: I’ve made a real-time 3D fluid simulation in WebGPUsplash-fluid.netlify.app
▲ 2matsuoka-601 560d 💬 6
15
newI made an AI for my native language Assamese
▲ 2Kabyanil 691d 💬 1
16
newShow HN: I Am 15 and Built a Dual Backend MLP from Scratch Using CUDA C++github.com
▲ 1muchlakshay 438d 💬 2
17
newShow HN: Tracking book mentions across podcast episodes
▲ 1steyeomans 299d discuss
18
newNvidia resurrects older graphics cards as RAM demands impact tech pricesmashable.com
▲ 4ripe 95d discuss
19
newLLM from scratch, part 28 – training a base model from scratch on an RTX 3090www.gilesthomas.com
▲ 540gpjt 306d 💬 121
20
newShow HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPUgithub.com
▲ 395xaskasdf 224d 💬 101
21
newRTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8imil.net
▲ 292iMil 113d 💬 108
22
newWe got 207 tok/s with Qwen3.5-27B on an RTX 3090github.com
▲ 165GreenGames 167d 💬 52
23
newCounter-Strike's Dust II runs purely within a neural network on an RTX 3090www.tomshardware.com
▲ 26bpierre 721d 💬 3
24
newShow HN: Local task classifier and dispatcher on RTX 3080github.com
▲ 26Shubham_Amb 240d 💬 2
25
newLaguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K contextwww.lucebox.com
▲ 20GreenGames 85d 💬 1
26
newBenchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090www.gilesthomas.com
▲ 16gpjt 71d discuss
27
newDual RTX 5060 Ti 16GB vs. RTX 3090 for Local LLMswww.hardware-corner.net
▲ 14pietrushnic 485d 💬 5
28
newStory of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090s
▲ 8yolo-auto 112d 💬 3
29
newEnabling Resizable Bar on RTX 3080 Vbios via GitHubgithub.com
▲ 7linux_lorax 140d 💬 5
30
newShow HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090github.com
▲ 6GreenGames 179d 💬 1
31
newQwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090github.com
▲ 5thc1006 166d 💬 2
32
newQwen 3.6 93B with MTP on 2×RTX 3090 NVLink=187 tokens/SEC,LLM lost bleat-a-thongithub.com
▲ 4devilfileprong 112d discuss
33
newQwen3.8-27B on a single RTX 3090: crash fix, 131K context, 9 mythsjonidimo.github.io
▲ 3jonaddb 47d 💬 2
34
newPFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090github.com
▲ 3GreenGames 156d 💬 1
35
newI swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090austinsnerdythings.com
▲ 3auspiv 172d discuss