Latest

Every published item, in order · 18 items

10月21日

MiniCPM-V 4.7 runs 35B MoE on phones at 20.51 tokens/s

Smarter scheduling, not a smaller model, is what makes a 35B-parameter MoE fit and run fast on consumer phones — no retraining required, since routing stays untouched. Developers building on-device multimodal apps can grab the code and weights from GitHub and Hugging Face to run large models where cloud calls are impractical. It also shows open-source Chinese labs pulling ahead on mobile inference efficiency, a space Apple and Qualcomm stack owners care about.

#MiniCPM #OpenBMB #on-device AI #MoE

OpenBMB@OpenBMBSource

10月20日

Models Builders21:01

Chinese contentMiniCPM-V 4.7 在 iPhone 上实现 20.51 tokens/秒本地多模态推理

OpenBMB 把 35B 多模态模型塞进 iPhone，每秒 20+ token，比基线快 6 倍，代码开源可以直接上手玩。

#MiniCPM #OpenBMB #多模态 #开源模型

OpenBMB@OpenBMBSource

Models Builders15:43

Chinese contentMiniCPM-V 4.7 发布：多模态模型本地跑，约 3 GB 内存

OpenBMB 的 MiniCPM-V 4.7 手机上就能跑多模态模型，100 tok/s 加 3 GB 内存，llama.cpp 一装就能试。

#MiniCPM-V #OpenBMB #llama.cpp #多模态

Event

OpenBMB@OpenBMB2 sourcesSource

Models Builders14:43

Chinese contentvLLM v0.32.0 支持 MiniCPM-V 4.7 推理部署

OpenBMB 的 MiniCPM-V 4.7 进了 vLLM v0.32.0，自己搭服务的可以直接用 vLLM 跑它了，吞吐延迟都更好。

#MiniCPM-V #vLLM #OpenBMB #多模态

OpenBMB@OpenBMBSource

10月19日

Models Builders11:37

Chinese contentMiniCPM-V 4.7 登上 Hugging Face 热榜第二

OpenBMB 的 MiniCPM-V 4.7 冲上 Hugging Face 热榜第二，35B-A3B MoE 手机端 3GB 内存就能跑，想玩端侧多模态的可以试试。

#MiniCPM-V #OpenBMB #Hugging Face #多模态

OpenBMB@OpenBMBSource

10月17日

Models Builders00:12

Chinese contentMiniCPM-V 4.7 1B 在 iPhone 上离线识别咖啡小票

面壁智能的 MiniCPM-V 4.7 1B 能直接在 iPhone 上离线读小票答问题，1B 模型本地跑多模态，这个演示挺直观。

#MiniCPM-V #面壁智能 #OnDevice LLM #多模态

官方账号面壁智能 ModelBest@ModelBest_AISource

10月15日

Models Builders17:18

Chinese contentMiniCPM-V 4.7 35B-A3B 并行编码测试：16 个 coding agent 同时运行

有人拿 MiniCPM-V 4.7 的 INT4 版本同时跑 16 个 coding agent，还配了 DSpark drafter，结果在这条帖子里能看到。

#MiniCPM-V #coding agent #开源模型 #量化

官方账号面壁智能 ModelBest@ModelBest_AISource

10月14日

Models US vs China22:46

Chinese content面壁开源MiniCPM-V 4.7：3G内存，iPhone断网跑多模态

面壁开源了MiniCPM-V 4.7，3G内存就能在iPhone上断网跑多模态，做端侧应用的可以直接上手试试。

#MiniCPM-V #面壁智能 #多模态 #开源模型

量子位@十三Source

Models BuildersSelected11:39

OpenBMB releases MiniCPM-V 4.7 multimodal model for phones

The core shift is system-level: LES moves the bottleneck from memory capacity to flash bandwidth and expert-prediction hit rate, letting a 35B-class model live on consumer phones without a cloud round-trip. Developers building on-device apps can fine-tune with SRFT's 4:1 task-to-replay data mix while keeping general abilities largely intact. Weights and code are on Hugging Face and GitHub, so teams can experiment today.

#MiniCPM-V #OpenBMB #open-source models #multimodal

shao__meng@shao__mengSource

10月13日

Models Builders21:25

Chinese contentMiniCPM-V 4.7 发布：35B 多模态 MoE 模型仅用 3GB 内存跑在手机上

OpenBMB 把 35B 的多模态模型塞进了 3GB 内存，手机能离线读文档、认路牌，还给了 1B 小版本和微调方法，端侧玩法直接变多了。

#MiniCPM-V #OpenBMB #MoE #多模态

OpenBMB@OpenBMBSource

Models BuildersMulti-source18:26

Chinese contentOpenBMB 发布 MiniCPM-V 4.7，3B 激活参数可在 iPhone 上运行

OpenBMB 放出了 MiniCPM-V 4.7，3B 激活参数就能在 iPhone 上跑到 13 tokens/s，性能还能压过参数多 10 倍的模型，本地跑多模态的朋友可以试试。

#MiniCPM-V #OpenBMB #Qwen #多模态

Event

Paul Couvert@itsPaulAi8 sourcesSource

Models Builders17:17

Chinese content面壁智能发布 MiniCPM-V 4.7：端侧 MoE 多模态模型，3GB 内存跑出 13+ token/s

面壁把 35B 的 MoE 模型塞进 3GB 内存的手机里还能跑 13+ token/s，比 Qwen3.6 同规格得分还高，做端侧应用可以看看。

#MiniCPM-V #面壁智能 #MoE #多模态

IT之家Source

Models BuildersSelected15:08

MiniCPM-V 4.7 open-source multimodal models released by ModelBest

The 35B-A3B MoE-style variant with only ~3B active parameters targets on-device multimodal inference, making it a candidate for deployment where cloud APIs are costly or unavailable. Developers in Southeast Asia building offline or low-bandwidth vision-language applications can download weights directly from Hugging Face under open-source terms and benchmark it against Qwen-VL alternatives.

#MiniCPM-V #ModelBest #open-source models #multimodal

官方账号面壁智能 ModelBest@ModelBest_AISource

Models Builders14:49

Chinese contentMiniCPM-V 4.7 联手 Nativ 实现苹果芯片端侧运行

OpenBMB 的 MiniCPM-V 4.7 现在能在 Mac 上离线跑多模态了，1B 版每秒 315 token，图像视频都能看，数据不出本地。

#MiniCPM-V #Nativ #多模态 #端侧推理

OpenBMB@OpenBMBSource

Models BuildersMulti-sourceSelected13:01

MiniCPM-V 4.7 runs 35B multimodal model on phones

The key change is deployment economics: a 35B MoE now fits consumer devices at usable speeds, because LES hides IO wait through scheduling instead of trading off precision. Developers building privacy-sensitive on-device apps should test it, since no cloud call is required. Against typical acceleration methods that cut quantisation levels and lose points, this keeps baseline accuracy intact.

#MiniCPM-V 4.7 #ModelBest #on-device models #open-source models

Event