openbmb/MiniCPM-V-4.7-1B
"MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant.
Proof1 community thread
Key points
- Notable features of MiniCPM-V 4.7 include:
- The 1B variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier for MLLMs. In Instruct mode, the 1B variant continues to improve foundation capabilities over MiniCPM-V 4.6 and substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.
- Based on the intra-ViT early compression technique from LLaVA-UHD v4, MiniCPM-V 4.7 compresses visual tokens early within the vision encoder, reducing computation in subsequent encoder layers.
- MiniCPM-V 4.7 supports inference frameworks including SGLang, vLLM, llama.cpp, and Ollama, along with fine-tuning frameworks including SWIFT and LLaMA-Factory.
Sources (1)
- [1]openbmb/MiniCPM-V-4.7-1Br/LocalLLaMA (top, daily) · Oct 12, 06:03 PM
"MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant.
Notable features of MiniCPM-V 4.7 include:
Extractive summary: sentences quoted from the sources.
Before this
- Oct 12, 2026openbmb/MiniCPM-V-4.7-35B-A3B
- Oct 12, 2026Deploy decision models with llama.cpp on Amazon SageMaker AI
- Oct 12, 2026unslothai/unsloth v0.1.906-beta: Browser Use + Qwen-Image-2.1-Turbo
- Oct 12, 2026Qwen3.8-Flash-Next on six 3090s with vLLM: 7 users at 262k, 6.5k t/s prefill, 57 t/s decode solo / 206 t/s aggregate with all 7 generating. Fixes for the upstream included.
- Oct 10, 2026vllm-sr/d3
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
