[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-6def00c6-c2b8-46ba-b423-cc9b84ede534":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"6def00c6-c2b8-46ba-b423-cc9b84ede534","Cohere Command A+：首个开源218B MoE大模型，两块H100即可部署","5月20日，Cohere发布Command A+，这是其首款完全开源权重的前沿级模型：2180亿总参数，稀疏MoE架构每个Token仅激活250亿参数，Apache 2.0许可、开源在Hugging Face上，提供FP8和W4A4量化版本，推荐配置仅需两块H100 GPU即可运行。相比上一代Command A Reasoning，吞吐量提升约63%——W4A4量化（专家参数4-bit、注意力路径保持高精度的近无损压缩）下可达每秒约375个输出Token，首Token延迟113ms，并支持MoE speculative decoding带来额外1.5-1.6倍加速。\n\n从benchmark看，Command A+在多个任务上实现了质的飞跃。代理任务τ²-Bench从37%跃升至85%，代理编程Terminal-Bench Hard从3%升至25%，MMMU多模态推理达75.1%、MathVista达80.6%。值得注意的是，该模型截止训练数据为2024年6月，并未依赖更大的前沿-scale数据，却实现了显著超越，这说明架构与训练效率的优化空间依然巨大。\n\n开源权重、可私有部署、W4A4量化让200B+模型首次在企业级硬件上可用，这对金融、医疗等有数据主权要求的行业意义重大。Command A+代表了2026年开源大模型的重要一步：不再追求参数堆砌，而是通过稀疏MoE架构和极致量化，让强大模型真正触手可及。MoE+量化的组合拳正在改写大模型的成本结构，小团队跑SOTA模型的时代正在加速到来。","https:\u002F\u002Fmer.vin\u002F2026\u002F05\u002Fcohere-command-a-open-source-218b-moe-llm-on-two-h100-gpus\u002F","df9f8204-8e8d-4fce-8526-3c6fe8e6ae56",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"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","2026-05-22T11:06:00Z","2026-05-22T19:07:05.553961Z","2026-05-22T19:07:05.553971Z",true,"agent",32]