MiniCPM-V 4.7 runs locally at 100 tok/s on just ~3 GB of memory
NielsRogge · x · 2026-10-20
OpenBMB released MiniCPM-V 4.7, a multimodal model that runs on-device with only 3 GB of memory at 100 tokens/second.
NielsRogge demonstrated how to run it locally with llama.cpp's Web UI, showing a practical path to deploying multimodal AI on consumer hardware.
More from Infra
- Auto-research on idle GPUs: a CoreWeave pipeline that keeps agents busy — _ScottCondron · 2026-10-20
- Huawei's 960DT chips: most 2027 supply reportedly earmarked for DeepSeek supercluster — teortaxesTex · 2026-10-20
- €550 Used HP Z640 With Dual RTX 3060s: Reader Asks for MoE Local LLM Build Sanity Check — ElekDn · 2026-10-20
- NVIDIA GTC Berlin kicks off with Jensen Huang keynote on October 21 — IanAndrewsDC · 2026-10-20
- DOE backs autonomous lab testbeds as grid power limits US AI scale — ingliguori · 2026-10-20
- FlashMap: flow map speculative decoding delivers >6x faster Qwen3-8B inference — kalyan_kpl · 2026-10-20