MoE编码模型太大跑不动？这篇论文提出一次性剪掉一半专家，编码能力几乎不变。
arXiv:2607.16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size come…
数据科学家亲测10款AI编码模型，5个任务评分+定价数据，帮你选最值工具。
I Ran 10 AI Coding Models Through 5 Tasks: A Data Scientist's Take I'll be honest — I went into this expecting a clear winner. I came out with a scatt…
M4 Max+128GB内存用户实测遭遇推理瓶颈，求推荐Apple Silicon上又快又好的编码模型，性能与成本如何平衡？
I have an M4 Max with 128 GB of unified memory, and I thought it would be easy to reach decent inference speeds with it. After a few failed attempts t…
16GB内存、无独显的办公本也能跑本地编码Agent？这篇HN问答推荐了多个轻量级模型方案
Claude Code like agentic workflow ai too costly for me.Any LLM can I run with VSCode at the below setup? 16ram Intel core i7 h processor 13gen 512gb N…
OpenAI推出GPT-5.1-Codex-Max，更快更智能，专为大规模项目级编码任务打造，推理与token效率双提升。
Introducing GPT-5.1-Codex-Max, a faster, more intelligent agentic coding model for Codex. The model is designed for long-running, project-scale work w…