1
Jamesob's guide to running SOTA LLMs locally
花2千美元配一套跑顶级本地大模型的机器，VRAM优先，老平台省一万，干货满满。
Article URL: https://github.com/jamesob/local-llm Comments URL: https://news.ycombinator.com/item?id=48775921 Points: 276 # Comments: 125
2
LLM Quantization Project Part 1: What Even Is an LLM?
从零拆解大模型本质，为量化项目打基础，零基础也能看懂。
Article URL: https://www.lttlabs.com/articles/2026/06/19/llm-quantization-part-1-what-even-is-an-llm Comments URL: https://news.ycombinator.com/item?i…
3
Ask HN: What's the best LLM model that on a 24 GB VRAM GPU?
24GB显存下寻找超越Qwopus3.6的8-bit LLM模型，生产可用性优先。
What’s the best model right now that outperforms Qwopus3.6-27B-v2-MTP-GGUF 8-bit on a 24 GB VRAM GPU? Looking for real reviews. I found 4 bit not usab…
4
Use your Nvidia GPU's VRAM as swap space on Linux
将NVIDIA显存当交换空间用，巧用CUDA驱动和NBD协议实现系统资源榨干。
Article URL: https://github.com/c0dejedi/nbd-vram Comments URL: https://news.ycombinator.com/item?id=48377404 Points: 269 # Comments: 70
5
Ask HN: Is the next big thing locally running coding agents?
当云端API成本飙升，本地运行开源模型完成编程任务或将成主流趋势。
There's extreme price escalation on part of Anthropic, with token spend now approaching levels that have made many-an-enterprise scratch their heads. …
6
What Models? Helps Match Local AI Models to Your Hardware
帮你根据GPU和显存快速匹配本地可运行的AI模型，无需再盲目下载测试
Article URL: https://whatmodelscanirun.com/ Comments URL: https://news.ycombinator.com/item?id=48216130 Points: 3 # Comments: 0