MiniCPM-V 2.6 8B
Multimodal MiniCPM at 8B. Vision + text; strong on document Q&A for the size class.
Overview
Multimodal MiniCPM at 8B. Vision + text; strong on document Q&A for the size class.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- MIT license
- Multimodal at 8B
Weaknesses
- Vision quality below 32B-class VLMs
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 5.0 GB | 7 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of MiniCPM-V 2.6 8B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run MiniCPM-V 2.6 8B?
Can I use MiniCPM-V 2.6 8B commercially?
What's the context length of MiniCPM-V 2.6 8B?
Does MiniCPM-V 2.6 8B support images?
Source: huggingface.co/openbmb/MiniCPM-V-2_6
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify MiniCPM-V 2.6 8B runs on your specific hardware before committing money.