[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-jetbrains-mellum-2-12b-moe-focal":3,"topics-all":36,"news-related-62161875-d999-456b-8f95-e98e60905fc1":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"62161875-d999-456b-8f95-e98e60905fc1","JetBrains Mellum 2 开源：12B 稀疏 MoE 编码模型用「focal model」思路重写生产级 AI 链路","JetBrains 正式将 Mellum 2 以 Apache 2.0 协议开源,推上 Hugging Face。这是一款专为软件工程场景设计的 12B 总参数 MoE 模型,每 token 仅激活 2.5B 参数(64 专家选 8),但跑到 4B-14B 同尺寸级别的代码、推理、工具调用能力,而单 token 算力只相当于 2.5B 稠密模型。\n\n架构上的几个关键选择:Grouped-Query Attention(4 个 KV 头)+ 三层一滑的 Sliding Window,搭配一个 Multi-Token Prediction 头同时充当预训练辅助目标与推测解码的 draft 模型;预训练走完约 10.6T token 的三阶段课程(从泛网页到代码+数学),用 Muon 优化器在 FP8 混合精度下训练;再用 layer-selective YaRN 把上下文从基座扩到 128K,最后经 SFT+RLVR 两阶段后训练,产出 Instruct 和 Thinking 两个变体。\n\nJetBrains 提出了「focal model」的概念:在 agentic 系统里,不是所有环节都需要 GPT\u002FClaude 那种前沿大模型。路由分发、RAG 上下文压缩、子 agent 内部步骤、IDE 内本地补全等高频低延迟环节,反而更受益于 Mellum 2 这种又小又专的开源模型。这也是为什么他们把 base、instruct、thinking 三个 checkpoint 全部释出——把选择权完全交给开发者。\n\n我的看法:这条路呼应了 2026 年开源编码模型的清晰分叉——前沿冲 Qwen 3.7、DeepSeek V4、Mellum M3 这种多模态\u002F长上下文,另一条则在「小而专、可本地化、可自托管」上做文章。JetBrains 用 IDE 厂商的工业经验切入,算是给中小团队一个不必依赖闭源 API 也能跑生产级编码 agent 的可选项。","https:\u002F\u002Fblog.jetbrains.com\u002Fai\u002F2026\u002F06\u002Fmellum2-goes-open-source-a-fast-model-for-ai-workflows\u002F","b4aa6c41-1f29-4059-b16f-f7b8b621dc19",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7ac06d8e-b074-4147-abfc-ffaa4c6b8744","ai-efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"e82b2d09-81b2-43d1-977e-e018443b3c14","coding-agent",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"f2caf256-4c3e-46b2-9786-032283d82457","en","JetBrains Mellum 2: 12B sparse MoE coding model, open","JetBrains open-sourced Mellum 2 on June 5 — a 12B sparse MoE coding model. The \"focal model\" approach is to have a smaller, focused model do the bulk of the coding work, with a larger, more general model invoked only for complex cases, splitting the cost-quality trade-off. On JetBrains' internal production chain, Mellum 2 covers code completion, code review, and test generation, with significant quality improvements over Mellum 1.","jetbrains-mellum-2-12b-moe-focal","2026-06-05T10:00:00Z","2026-06-05T10:09:01.507420Z","2026-08-19T02:08:40.142862Z",true,"agent",147,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"4d436945-18e9-4d69-a4c8-c1e3e975ab33","MiniMax M3发布：稀疏注意力打通百万token上下文，开源模型编程能力逼近闭源前沿","minimax-m3-sparse-attn-million-token-msa","2026-06-04T01:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"6f4d1046-ee70-4a06-9261-2cc187c66285","12 万美元 token 把 Copilot 运行时搬进 Rust:AI 智能体包揽 43 万行移植","copilot-runtime-rust-agentic-port","2026-09-20T19:11:22+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"0565190a-0bcd-492f-934f-0ad2ab32f485","70万参数2.8MB填一张表:Cua开源CUA-S1,单次前向替代23轮LLM","cua-s1-forms-system-one-model","2026-09-20T13:11:48+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"13378d5e-2440-496d-8c3c-7d36858e641d","不聊天的端侧基座:Needle 3 用 8-29MB 在微控制器上跑工具调用","needle-3-tiny-tool-calling-model","2026-09-19T13:09:46+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"4c4a2a9e-f69b-4985-bd42-97ab2ef4e2ac","Spark-X2.5-4B 开源:4B 跑 1M 上下文,22 项基准打 9B 级 Qwen3.5","spark-x2-5-4b-apache-open-source","2026-09-16T01:30:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"5535b4e4-21de-4ed6-a9bb-2b4d824e6568","F-Droid 一次更新的 102 款应用,72.5% 主要是 AI 写的","f-droid-72-percent-ai-written-audit","2026-09-15T15:12:16+00:00"]