Low confidenceNot in digests or recommendations.
MiniCPM-V 4.7 1B DSpark
MiniCPM-V 4.7 1B DSpark is a draft model trained for MiniCPM-V 4.7 1B. The source links to its separately released model artifact.
What it does
Use it to analyze images and videos locally or through a serving framework.
- Availability
- Model weights and a live demo are linked.
- Pricing model
- Not established
- Deployment
- Supports iOS, Android, HarmonyOS, and local deployment.
- Privacy
- Not established
- Licence
- Not established
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model supports single-image, multi-image, and video understanding.
- It supports mixed 4x/16x visual token compression.
- Model weights, inference instructions, and a live demo are linked.
- It supports deployment on iOS, Android, and HarmonyOS.
- It supports chip platforms from Rockchip, Houmo, Intel, AMD, and Arm.
- FP8 quantization support is available.
Sources
1
1
OpenBMBOwner-controlled
https://huggingface.co/openbmb/MiniCPM-V-4.7-1B
Retrieved 2026-10-29 00:58 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-15 19:27 UTC | evidence update | score | Current |
| 2 | 2026-10-14 20:18 UTC | material change | capability, modality, access, deployment, availability, deployment | Current |
| 1 | 2026-10-12 22:08 UTC | publication | None | Current |
In briefs
1- Muse Wonder is aimed at document work, workflows, and coding Daily brief 2026-10-12
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.