MiniCPM-V 4.7 Heretic

An abliterated variant of MiniCPM-V-4.7-1B. Refusal directions were identified and surgically removed from the model weights using heretic’s direction-ablation pipeline, reducing refusal behavior while keeping the base model’s capabilities intact.

Heretic Details

Low KL divergence (0.0122) indicates the abliterated model stays numerically close to the base. The ²¹⁄₁₀₀ refusal rate is a meaningful reduction from the base model while avoiding capability degradation.

Note: No model is fully “uncensored.” A small residual refusal rate remains on the most deeply-trained refusal categories — this is expected and preferable to the capability loss incurred by more aggressive ablation.

Usage

Run with Ollama:

ollama run maternion/minicpm-v4.7-heretic:1b

All tags include the vision projector (mmproj), so image input works out of the box.

MiniCPM-V 4.7

GitHub · Evaluation · Examples · Model weights

MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family’s single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference. Notable features of MiniCPM-V 4.7 include:

• 🔥 A New Pareto Frontier in Performance and Efficiency. As model capabilities continue to advance, inference efficiency has become an important measure of a model’s value. On resource-constrained devices, delivering the strongest possible capabilities within a limited resource budget calls for higher capability density. 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.
• 🚀 Efficient Architecture. 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. It also supports mixed 4x/16x visual token compression, allowing developers to balance visual detail and inference cost across tasks.
• 💻 Broad Platform and Chip Support. MiniCPM-V 4.7 supports iOS, Android, and HarmonyOS, together with open-source on-device deployment support. It also provides day-0 support for chip platforms from Rockchip, Houmo, Intel, AMD, and Arm, extending deployment options across mobile and local computing devices.
• 🛠️ Developer Friendly. MiniCPM-V 4.7 supports inference frameworks including SGLang, vLLM, llama.cpp, and Ollama, along with fine-tuning frameworks including SWIFT and LLaMA-Factory. It provides GGUF, BNB, AWQ, and GPTQ quantized variants and adds FP8 quantization support.

Evaluation

Significantly Advancing the Performance–Efficiency Pareto Frontier

The 1B variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier. In Instruct mode, 1B substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.

Overall Performance (1B, Instruct)

Examples

MiniCPM-V 4.7 can run on phones and tablets. The clips below are unedited screen recordings captured directly on the devices.

1B iPhone 17 Pro Max

Model Weights

MiniCPM-V 4.7 is available in the following variants:

Acknowledgements

We would like to thank the following projects:

• Qwen3.5 and Qwen3.6 for providing the language backbone
• SigLIP2 for providing the vision understanding module
• Transformers