Latest

Every published item, in order · 24 items
10月21日
ModelsBuildersSelected21:07
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.

OpenBMB@OpenBMBSource
10月20日
10月19日
10月17日
10月16日
10月15日
10月14日
ModelsBuildersSelected11:39
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.

shao__meng@shao__mengSource
How-toBuildersMulti-sourceSelected11:14
MiniCPM-V 4.7 1B Hands-On: Local Setup With Ollama

A 1B multimodal model that runs locally via Ollama or llama.cpp lowers the hardware bar for on-device vision tasks, useful when privacy or latency rules out cloud APIs. Developers testing small models on edge devices can use the walkthrough's reported failures to calibrate expectations before installing. MiniCPM-V comes from ModelBest, a Chinese lab, so it can be compared against Qwen's small multimodal variants at similar sizes.

Event
官方账号面壁智能 ModelBest@ModelBest_AI4 sourcesSource
10月13日
ModelsBuildersSelected15:08
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.

官方账号面壁智能 ModelBest@ModelBest_AISource
ModelsBuildersMulti-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.

Event
AIGCLINK@aigclink6 sourcesSource
9月17日
AITOP16:09
Anthropic拟10月在新加坡设亚太第五个办事处 开...

Anthropic拟10月在新加坡设亚太第五个办事处 开放本地招聘 数据显示,按人口比例计算,新加坡的Claude.ai使用水平在121个国家中排名第二。 我们观察到,人工智能公司Anthropic计划于10月在新加坡设立其亚太地区的第五…

AITOPRead
8月13日
8月7日
AITOP17:04
出口结构剧变:中国卖给世界的,不再是产品而是解法

中国出口"新新三样":从打火机到爬墙机器人,世界不再只是买便宜货 我们观察到一组清晰的数据信号:中国出口的"新新三样"已经从过去的服装、家具、家电,换成机器人、AI模型和创新药物。这不是产业升级的修辞游戏,而是发生在澳大利亚和巴西的实证样…

AITOPRead
8月2日