MiniCPM-V 4.7
ClosedMultimodalVision
MiniCPM-V 4.7 is a multimodal vision-language model from ModelBest (面壁智能), released on 2026-10-12 as the newest entry in the MiniCPM-V series. Weights are not open.
—context
—per 1M tokens (in / out)
—parameters
26stories in our feed
Specs
hover a value to see its sourceContext window—
Max output—
Parameters—
Knowledge cutoff—
Licence—
Commercial useUnknown
Input—
Output—
Familyminicpm
API price
USD per 1M tokensNo public API price yet.
2026-10-21
2026-10-20
MiniCPM-V 4.7 本地跑通自动化报告生成工作流OpenBMB
2026-10-19
用 MiniCPM-V 4.7 搭建视频自动解说工具 Clip Narrator面壁智能 ModelBest
2026-10-16
MiniCPM-V 4.7 35B-A3B 在 Mac 上离线生成可玩的 Tetris 游戏面壁智能 ModelBest
2026-10-15
MiniCPM-V 4.7 接入 Claude Code,跑通编码工作流面壁智能 ModelBest
2026-10-14
MiniCPM-V 4.7 1B Hands-On: Local Setup With Ollama面壁智能 ModelBest
2026-10-13
2026-10-12
Atomic Chat 发布去审查版 MiniCPM-V 4.7 35B-A3B@atomic_chat_hq
MiniCPM-V 4.7 在 Pagoda 测试中击败 Qwen 3.6 35B-3A@atomic_chat_hq