Sakura 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 5 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.
Sakura MiniCPM V 4.7 1B – a 1B vision‑language model
Sakura MiniCPM V 4.7 1B is a 1.01B parameter model built on the qwen35 architecture. It supports reasoning, tools, and vision tasks and is available in several GGUF quantizations. The model is licensed under apache-2.0.
Good at
- Reasoning
- Vision understanding
- Tool usage
Limits
- No vision support without mmproj
- Requires llama.cpp build with MiniCPM‑V 4.7 projector
- Limited to 262144 context tokens
Best for
- On‑device inference
- Mobile and local computing
- Fine‑tuning with SWIFT or LLaMA‑Factory
Who it’s for. Developers building on‑device vision‑language applications who need a lightweight 1B model. The model is suitable for Android, iOS, HarmonyOS, and various chip platforms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 0.67 GB, memory 1.6 GB at 8k context). For 4 GB VRAM, use IQ4_XS (0.64 GB, 1.5 GB). For 2 GB VRAM, use Q4_K_M if available, otherwise Q5_K_M (0.75 GB, 1.7 GB).
What GPU do you need for Sakura 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 Sakura MiniCPM V 4.7 1B quant should you choose?
Q4_K_M is the usual starting point for Sakura 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 Sakura MiniCPM V 4.7 1B
How much VRAM does Sakura 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 Sakura 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 Sakura MiniCPM V 4.7 1B GGUF?
It depends on the quant: IQ4_XS is 0.6 GB, Q4_K_M is 0.7 GB, Q5_K_M is 0.8 GB, Q6_K is 0.8 GB, Q8_0 is 1.1 GB.
What context length does Sakura 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 Sakura MiniCPM V 4.7 1B GGUF?
The files are on Hugging Face in the webmp3/Sakura-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 Sakura 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 Sakura MiniCPM V 4.7 on 8 GB VRAM?
Yes, the Q4_K_M quantization uses approximately 1.6 GB of VRAM at 8k context, which fits within an 8 GB budget.
Does the model support image input?
Image input requires a llama.cpp build that knows the MiniCPM‑V 4.7 projector and the mmproj file. Without it, only text is supported.
What license does the model use?
The model is released under the apache-2.0 license.