Edge0 发布 Edge0-145B 和 Edge0-120B 开源权重模型，可在本地笔记本运行
100B 级模型塞进笔记本本地跑，Terminal-Bench 2.1 上还赢了 Claude Opus 4.6。29G 内存、离线免费、代码不出本机，写代码的人可以直接下权重试试。
Edge0_AI 发布首批设备原生 100B 级基础模型 Edge0-145B 和 Edge0-120B，开放权重并已上传 Hugging Face。两款模型可在本地离线运行，主打无需云端 API、无 token 费用、代码与数据不出本机。在 Terminal-Bench 2.1 编程基准上，Edge0-145B 得分 86.5%，超过 Claude Opus 4.6 的 78.2%。
资源占用方面，模型只需 29G 显存/内存，约为标准部署配置（100G+）的三分之一。在 RTX Spark 和 Mac 上解码速度超过 75 toks/s，prefill 速度超过 1050 toks/s。模型支持 128K–256K token 上下文，长任务下速度不下降。用户可在本地运行，也可接入自己喜欢的编程智能体框架。
这一发布把 100B 级模型从数据中心拉到了消费级设备，与依赖云端 API 的 Claude 等闭源模型形成差异化路线，对关注本地化、数据隐私的独立开发者和企业有直接参考价值。
great job！ Samuel Zeng @SamuelZengML Introducing Edge0-145B and Edge0-120B, @Edge0_AI ’s first device-native 100B-class foundation models with open weights. Cloud-level intelligence on your laptop. Free, offline, and fast enough for real vibe coding. - Smart: beats Claude Opus 4.6 on Terminal-Bench 2.1 (86.5% vs. 78.2%) - Light: needs just 29G memory, 1/3 of a standard setup (100G+) - Fast: decodes 75+ toks/s, prefills 1050+ toks/s on RTX Spark and Mac. - Steady: handles 128K–256K tokens of context without slowing down, even on long tasks Frontier-class agentic coding. No cloud API. No token bill. Your code and data never leave your machine. Open weights are live on @huggingface . Run it locally or plug it into your favorite coding agent.
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Edge0, Terminal-Bench, 开源模型, 编程助手.
Source attribution: curated from AI Will (@FinanceYF5).
