MiniCPM V 4.7 35B A3B needs about 20.9 GB of memory at its main file (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
MiniCPM‑V 4.7 35B‑A3B – a 35B‑parameter MoE model with vision, reasoning, and tools support
MiniCPM‑V 4.7 35B‑A3B is a 34.7 billion‑parameter mixture‑of‑experts model built on the qwen35moe architecture. It supports reasoning, tools, and vision tasks and was trained on 262144 context tokens. The model is released under the apache‑2.0 license.
Good at
- Multimodal reasoning
- Tool‑use integration
- Vision understanding
Limits
- Requires 20.9 GB VRAM at 8K context
- No explicit vision support beyond single‑image input
- License is apache‑2.0
Best for
- On‑device inference with limited GPU memory
- Multimodal chat applications
- Research on MoE efficiency
Who it’s for. Developers building multimodal LLMs who need a mixture‑of‑experts model that fits on devices with around 20 GB VRAM. Researchers interested in MoE performance‑efficiency trade‑offs will also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 19.7 GB | 20.9 GB | Too big | Get file → |
The only available GGUF file is quantized as unknown and has a file size of 19.71 GB. It estimates 20.9 GB VRAM usage at 8K context. For a 24 GB VRAM budget, this is the recommended quant. No other quantizations are provided.
What GPU do you need for MiniCPM V 4.7 35B A3B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (19.7 GB file, about 20.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniCPM V 4.7 35B A3B
How much VRAM does MiniCPM V 4.7 35B A3B need?
About 20.9 GB at its main file with an 8K context window. That is the 19.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run MiniCPM V 4.7 35B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiniCPM V 4.7 35B A3B GGUF?
It depends on the quant: file is 19.7 GB.
What context length does MiniCPM V 4.7 35B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download MiniCPM V 4.7 35B A3B GGUF?
The files are on Hugging Face in the WhiskyAKM/MiniCPM-V-4.7-35B-A3B-NVFP4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MiniCPM V 4.7 35B A3B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MiniCPM‑V 4.7 35B‑A3B on 8 GB VRAM?
No, the model requires approximately 20.9 GB VRAM at 8K context, which exceeds an 8 GB budget.
Does the model support vision tasks?
Yes, it has detected vision ability and supports single‑image input.
What license applies to this model?
The model is released under the apache‑2.0 license.