1
Show HN: AI-CLI – tiny C terminal assistant powered by local LLM
本地LLM驱动的终端AI助手，C语言编写，轻量小巧又实用
Article URL: https://github.com/vkataev/ai-cli Comments URL: https://news.ycombinator.com/item?id=48918840 Points: 3 # Comments: 1
2
Build a Local LLM Chatbot with Ollama and Python
手把手教你用Ollama和Python搭建本地大模型聊天机器人，零门槛运行AI
Build a Local LLM Chatbot with Ollama and Python Build a Local LLM Chatbot with Ollama and Python Imagine typing a question into your chatbot and gett…
3
Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)
基于OpenJDK Panama FFM的Java 22低延迟本地LLM运行器，统一硬件编排与零分配ABI，线程安全C API实现零拷贝编译。
I wanted to run AI from inside the JVM. I started out with the standard REST sidecar, ripped that out to use Project Panama (Foreign Function & Memory…
4
DGX Spark Local LLM Benchmark: Administrative Tasks
13款本地LLM跑分对比，Qwen3.6在行政任务中表现最优，唯一通过PDF转日历测试。
Article URL: https://www.aai-labs.com/en/research/local-llm-benchmark-administrative-tasks Comments URL: https://news.ycombinator.com/item?id=48809994…
5
Collabora Office Update with Choose Your Own LLM Adventure
办公套件Collabora Office更新，可自由选择不同大模型作为AI助手，提升文档处理效率。
Article URL: https://www.heise.de/en/news/Collabora-Office-26-04-Desktop-suite-with-self-selected-AI-11351930.html Comments URL: https://news.ycombina…
6
Buy or wait on local LLM hardware during the memory crunch
本地运行大模型正面临内存紧缺，是现在入手硬件还是继续观望？这篇文章帮你理清关键权衡点。
Article URL: https://thefrontierlab.ai/buy-or-wait-local-llm-hardware/ Comments URL: https://news.ycombinator.com/item?id=48760089 Points: 2 # Comment…
7
Ragit – chat with any folder of documents using a local LLM
用本地大模型与文档文件夹对话的开源工具，支持RAG和Ollama
Article URL: https://github.com/ats4321/ragit Comments URL: https://news.ycombinator.com/item?id=48743123 Points: 2 # Comments: 0
8
Good article about local LLM on MacBook Air
Ollama新MLX引擎让MacBook Air本地运行LLM速度翻倍，实测效果惊人。
Article URL: https://www.xda-developers.com/ollama-new-mlx-engine-local-llm-mac-twice-fast/ Comments URL: https://news.ycombinator.com/item?id=4872989…
9
Ask HN: How close are we to local LLMs being useful? What's the impact?
探讨本地大模型究竟何时能实用，以及它对摆脱数据中心依赖、打破寡头垄断的潜在影响。
Feels to me like local models are an under-covered aspect of this whole AI boom. If everything improves over time, at some point a good chunk of tasks…
10
Native Coding Agent Optimized for Local LLM and DeepSeek v4 with Vector Memory
终端编码代理，集成DeepSeek V4 Pro等模型，支持本地LLM与向量记忆，每小时成本仅0.40美元，高效智能编程。
Article URL: https://code.intellios.ai Comments URL: https://news.ycombinator.com/item?id=48563214 Points: 1 # Comments: 0
11
I built a 3B lease risk scanner that runs without an external LLM API
无需外部API，一个3B参数模型就能帮你看懂租赁合同里的隐藏风险。
I built Lease Lens for the Hugging Face Build Small Hackathon . The idea is simple: most people sign contracts they do not really read. That is true f…
12
Making Local LLM Fast
本地LLM提速秘笈：从Prefill到Decode，两分钟看懂推理加速核心环节
Article URL: https://bogdan.nimblex.net/programming/2026/06/10/making-local-llm-fast.html Comments URL: https://news.ycombinator.com/item?id=48489344 …
13
My $0/Month AI Stack as a Solo Mac Dev — What I Actually Use in 2026
独立Mac开发者分享零成本AI工具栈，用Gemini免费API替代本地大模型，适合个人开发者参考。
All tests run on an 8-year-old MacBook Air. All results from shipping 7 Mac apps as a solo developer. No sponsored opinion. I've shipped 7 paid Mac ap…
14
Gemma 4 E4B as a primary local LLM (replaced Qwen)
从Qwen换到Gemma 4 E4B：本地大模型的新选择，性能与易用性如何？
Article URL: https://digg.com/ai/bfr4bqhh Comments URL: https://news.ycombinator.com/item?id=48437537 Points: 2 # Comments: 0
15
Bonsai Browser: Reader-mode for every page, powered by a local LLM, Nothing Else
本地大模型驱动的浏览器阅读模式，无需联网即可为任意网页生成清爽排版，隐私与效率兼得。
Article URL: https://drive.google.com/drive/folders/1qDYvycW4Ki0gAppMGhvSixUCioIRXcmN Comments URL: https://news.ycombinator.com/item?id=48417644 Poin…
16
Large companies can add a local LLM filter layer to reduce their AI costs
大型企业可通过部署本地LLM过滤层，在保障性能的同时显著削减云端AI调用成本。
Article URL: https://umrashrf.github.io/large-companies-can-add-a-local-llm-filter-layer-to-considerably-reducing-their-ai-costs/ Comments URL: https:…
17
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
提出跨语言令牌套利新方法，用本地LLM预处理重写提示词，低成本优化代码代理上下文窗口。
arXiv:2606.03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input dri…
18
Microsoft forms partnership with Unsloth AI about local LLM execution
微软与Unsloth AI宣布合作，聚焦本地大模型执行，或推动边缘AI新方向。
Article URL: https://xcancel.com/UnslothAI/status/2061925637892297122 Comments URL: https://news.ycombinator.com/item?id=48381283 Points: 1 # Comments…
19
I ran a few local LLM models on my MacBook Air M3, these are the results
16GB MacBook Air M3实测：4B与8B模型速度差异可接受，关键是“适配”与“交换”决定生死。
Article URL: https://prasadkhake.com/blog/16gb-mac-llm Comments URL: https://news.ycombinator.com/item?id=48358776 Points: 3 # Comments: 0
20
Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows
本地大模型如何兼顾翻译质量与客户数据保密？这篇论文为自由译员提供了实测基准答案
arXiv:2605.31452v1 Announce Type: new Abstract: Building on our previous work, this paper develops practical, low-barrier methods for freelance transl…