Hackernews posts about RTX 3070

RSS feed for RTX 3070

01
newI Built a System One Model on a RTX 3070twitter.com
▲ 3lafalce 16d discuss
02
newTuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090sdoug.sh
▲ 5dougcalobrisi 20d 💬 1
03
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 2ibobev 24d discuss
04
newSingle-slot low-profile 75W RTX 3060 with no power connectors disappointswww.tomshardware.com
▲ 2sbulaev 29d discuss
05
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 1gpjt 25d discuss
06
newQwen3.8-Flash-Next 177B running at 11–15 tok/s on 1 RTX 5070 12GB and 32GB RAMgithub.com
▲ 1maziianobeatz58 38h discuss
07
newRunning Qwen3:30B MoE on an RTX 3070 laptop with Ollamablog.kekepower.com
▲ 18kekePower 490d 💬 1
08
newMemtest Vulkan v0.5.0 Benchmark on RTX 3070 Laptop GPUblog.axiomgaming.net
▲ 2Blake_Welsh 414d 💬 1
09
newFather fixes dead RTX 3070 with a jerry-rigged capacitor from an old radiowww.tomshardware.com
▲ 2speckx 87d discuss
10
newFully-functional RTX 3070 16GB gets frankensteined into existencewww.tomshardware.com
▲ 2Timofeibu 144d discuss
11
newShow HN: Building a local FIX protocol triage agent on an RTX 3070domgalati.substack.com
▲ 2dgalati 163d discuss
12
newShow HN: QLoRA fine-tuning in .zse INT4 format by ZSE
▲ 1zyoralabs 215d discuss
13
newShow HN: Qantify – GPU-Accelerated Trading Library with Advanced Math and AutoMLgithub.com
▲ 1Alradyin 326d discuss
14
newLLM from scratch, part 28 – training a base model from scratch on an RTX 3090www.gilesthomas.com
▲ 540gpjt 307d 💬 121
15
newShow HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPUgithub.com
▲ 395xaskasdf 226d 💬 101
16
newRTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8imil.net
▲ 292iMil 114d 💬 108
17
newWe got 207 tok/s with Qwen3.5-27B on an RTX 3090github.com
▲ 165GreenGames 168d 💬 52
18
newCounter-Strike's Dust II runs purely within a neural network on an RTX 3090www.tomshardware.com
▲ 26bpierre 722d 💬 3
19
newShow HN: Local task classifier and dispatcher on RTX 3080github.com
▲ 26Shubham_Amb 241d 💬 2
20
newLaguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K contextwww.lucebox.com
▲ 20GreenGames 86d 💬 1
21
newBenchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090www.gilesthomas.com
▲ 16gpjt 72d discuss
22
newDual RTX 5060 Ti 16GB vs. RTX 3090 for Local LLMswww.hardware-corner.net
▲ 14pietrushnic 486d 💬 5
23
newStory of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090s
▲ 8yolo-auto 113d 💬 3
24
newEnabling Resizable Bar on RTX 3080 Vbios via GitHubgithub.com
▲ 7linux_lorax 141d 💬 5
25
newShow HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090github.com
▲ 6GreenGames 180d 💬 1
26
newQwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090github.com
▲ 5thc1006 167d 💬 2
27
newQwen 3.6 93B with MTP on 2×RTX 3090 NVLink=187 tokens/SEC,LLM lost bleat-a-thongithub.com
▲ 4devilfileprong 113d discuss
28
newQwen3.8-27B on a single RTX 3090: crash fix, 131K context, 9 mythsjonidimo.github.io
▲ 3jonaddb 48d 💬 2
29
newIs the Nvidia RTX 3060 the best value for entry level local AI?aiflux.substack.com
▲ 3ericdotlee 377d 💬 2
30
newPFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090github.com
▲ 3GreenGames 157d 💬 1
31
newI swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090austinsnerdythings.com
▲ 3auspiv 173d discuss
32
newFine-Tuning Nvidia's GR00T 2B Robotic Model on a RTX 3090twitter.com
▲ 3nprobably 560d discuss
33
newNvidia RTX 3060 returns to retail 5 years after original launch, priced at $339www.tomshardware.com
▲ 2akyuu 86d discuss
34
newBalder v7 – 100% on SWE-bench Verified on a single RTX 3060
▲ 1BalderForseti 73d 💬 1
35
newNvidia rumored to bring GeForce RTX 3060 production back this quartervideocardz.com
▲ 1alecco 272d 💬 1
36
newBenchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090www.gilesthomas.com
▲ 1ibobev 70d discuss