MiniCPM-V-4.7-1B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.6 GB (IQ4_XS) to 1.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
MiniCPM‑V 4.7 1B – a compact vision‑enabled LLM for local inference
MiniCPM‑V 4.7 1B is a 1 B parameter model that supports single‑image, multi‑image, and video understanding. It is optimized for on‑device inference with efficient visual encoding and a small file size. The model is released under the Apache‑2.0 license.
Good at
- Vision‑enabled text generation
- Efficient on‑device inference
- Supports mixed 4x/16x visual token compression
Limits
- Requires at least 8 GB VRAM for Q8_0 at 8k context
- No native vision support beyond single‑image input
- Limited to 262 144 token context
Best for
- Mobile LLM apps needing image understanding
- Edge devices with limited VRAM
- Rapid prototyping of vision‑LLMs
Who it’s for. Developers building local AI applications that need image or video understanding without large GPU resources. The model is suitable for mobile, embedded, and on‑device deployments on iOS, Android, and HarmonyOS.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q6_K (0.84 GB file, ~1.7 GB memory at 8k context). For tighter budgets, IQ4_XS (0.59 GB file, ~1.5 GB memory) is a good trade‑off. Q8_0 offers the highest fidelity but needs ~1.08 GB file and ~2 GB memory.
What GPU do you need for MiniCPM-V-4.7-1B?
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: the best quant that fits is Q8_0 (1.1 GB file, about 2.0 GB in use).
Which MiniCPM-V-4.7-1B quant should you choose?
Q4_K_M is the usual starting point for MiniCPM-V-4.7-1B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ4_XS at 0.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniCPM-V-4.7-1B
How much VRAM does MiniCPM-V-4.7-1B need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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-4.7-1B on an 8 GB GPU?
Yes, with Q8_0: the 1.1 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM-V-4.7-1B GGUF?
It depends on the quant: IQ4_XS is 0.6 GB, IQ4_XS is 0.7 GB, Q4_K_M is 0.7 GB, Q5_K_M is 0.7 GB, Q5_K_M is 0.7 GB, Q6_K is 0.8 GB and 2 more.
What context length does MiniCPM-V-4.7-1B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download MiniCPM-V-4.7-1B GGUF?
The files are on Hugging Face in the AtomicChat/MiniCPM-V-4.7-1B-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-4.7-1B 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 1B on 8 GB VRAM?
Yes, the Q6_K quantization requires about 1.7 GB memory at 8k context, which fits within an 8 GB VRAM budget.
Does the model support video input?
The model supports video understanding, but the provided GGUF files are optimized for single‑image and multi‑image tasks.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.