Hackernews posts about RTX 3070
- 01
- 02
- 03LM Studio vs. Ollama on Linux: same model files, measured on an RTX 3090homebrewserver.club
- 04Llama.cpp v1.0 on an RTX 3090: up to 55% faster with speculative decodinghomebrewserver.club
- 05Nvidia RTX 20, 30, and 40-series GPUs hacked to remove a half-speed AI throttlewww.tomshardware.com
- 06
- 07
- 08Show HN: Castellan – A real-time strategy game for agentsrts.emersoftware.cl
- 09Running Qwen3:30B MoE on an RTX 3070 laptop with Ollamablog.kekepower.com
- 10I Built a System One Model on a RTX 3070twitter.com
- 11Memtest Vulkan v0.5.0 Benchmark on RTX 3070 Laptop GPUblog.axiomgaming.net
- 12Father fixes dead RTX 3070 with a jerry-rigged capacitor from an old radiowww.tomshardware.com
- 13Fully-functional RTX 3070 16GB gets frankensteined into existencewww.tomshardware.com
- 14Show HN: Building a local FIX protocol triage agent on an RTX 3070domgalati.substack.com
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090www.gilesthomas.com
- 24Dual RTX 5060 Ti 16GB vs. RTX 3090 for Local LLMswww.hardware-corner.net
- 25
- 26
- 27
- 28
- 29
- 30
- 31Qwen3.8-27B on a single RTX 3090: crash fix, 131K context, 9 mythsjonidimo.github.io
- 32Is the Nvidia RTX 3060 the best value for entry level local AI?aiflux.substack.com
- 33
- 34I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090austinsnerdythings.com
- 35
- 36Extending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
- 37Single-slot low-profile 75W RTX 3060 with no power connectors disappointswww.tomshardware.com
- 38Nvidia RTX 3060 returns to retail 5 years after original launch, priced at $339www.tomshardware.com
· edit