#Local models

#Local models

0 items today

10/2Fri

Friday

03:11
Shreya Shankar@sh_reyaAI score3636
用决策模型（如 Jev）逐行调用 API 处理数千行数据效率极低，无法利用查询规划。在单张 H100 上，Qwen3-4B 对 5k 条电影评论做一次 AI 过滤的理论最快速度约为 6.6 秒，目前包括开源 AI-SQL 引擎 Quail 在内的任何系统都远未接近。新博客文章介绍了 Quail 如何基于这一速度上限估算 AI 过滤器的成本。
Awaiting translation
Practice #Problems/pitfalls #Costs/usage limits #Local models

9/15Tue

Tuesday

00:30
Cline · BlogSelectedAI score6262
Cline releases the open-source desktop app Cline Desktop, aimed at open-weight models.
Cline has released an early version of its open-source desktop app, Cline Desktop, moving the agent runtime that previously lived in the VS Code extension and CLI into a standalone workspace. It supports parallel sessions, scheduled tasks, and a Marketplace for extending tools and integrations.
Releases #Product updates #Agent #MCP/tool use
Why it matters: The official release lays out the desktop app's capabilities and open entry points, so readers can judge whether it fits their multi-agent parallel workloads.

8/27Thu

Thursday

04:44
Cline · BlogSelectedAI score7171
Cline 实测八个模型做 IMO 2026：DeepSeek V4 Flash 以 0.12 美元拿到金牌线
Cline 让八个模型在自家 harness 里做 IMO 2026 六道题，证明由 GPT-5.5 和 Claude Opus 5 双盲按 0–7 分制评分、Gemini 3.1 Pro 仲裁，金牌线为 29 分。
Awaiting translation
Releases #Reviews/benchmarks #Open-source models #DeepSeek
Why it matters: Cline 用同一套 harness 盲评八个模型做 IMO 2026，给出分数与单次成本对照，可看开源权重模型的实际性价比。