跳到正文
原文
rohanpaul_ai· @rohanpaul_ai · X·· 1 天前AI 评分66

微软 Copilot 将常规编码任务从 Claude Haiku 4.5 切换到端侧 MAI-Code-1.1-Flash

AI 导读

微软宣布 Copilot 将把常规编码任务从 Anthropic 的 Claude Haiku 4.5 交给运行在 Nvidia PC 上的端侧模型 MAI-Code-1.1-Flash(137B 总参数、6.8B 激活参数),模型路由器把常规工作留在本机,本地调用不收推理费用。

正文 · 原文

Microsoft just announced that Copilot will hand routine coding from Anthropic's Claude Haiku 4.5 to Microsoft's MAI-Code-1.1-Flash (a 137B total and 6.8B active param model) running on Nvidia-powered PCs

A model router will keep th routine work on the machine and this local model calls carry no inference charge.

The on-device MAI-Code-1.1-Flash uses 3-bit quantization yet keeps its 256K-token context window, and Microsoft says it scores the same as full precision on SWE-Bench Verified and Terminal-Bench 2.1.

Microsoft's hardware for the shift is the Surface Laptop Ultra from $2,599 and the Surface RTX Spark Dev Box from $5,999

Both run on Nvidia's RTX Spark, an Arm-based chip with a Blackwell GPU and up to 128GB of memory shared by processor and graphics.

Also, Microsoft made its agent sandbox, Microsoft Execution Containers (MXC), generally available on Windows 11. Companies can now set which files and network locations an agent may use, and Windows blocks everything else while the agent runs, with isolation levels ranging from separate processes and sessions up to virtual machines and cloud PCs.

来源:rohanpaul_ai · x.com