MI

Sakura MiniCPM V 4.7 1B Uncensored

MiniCPMGGUF by webmp3Updated 2026-10-17
Download on Hugging Face
Parameters1.01B
Context256K
Layers24
Architectureqwen35
Smallest quant0.6 GB
Quick answer

Sakura MiniCPM V 4.7 1B Uncensored 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 Uncensored – a 1B vision‑language model in GGUF format

Sakura MiniCPM V 4.7 1B Uncensored is a 1.01‑billion parameter model based on the qwen35 architecture. It supports single‑image, multi‑image, and video understanding with efficient visual encoding. The model is available in several GGUF quantizations and is licensed under apache‑2.0.

Good at

  • Vision‑language tasks
  • Efficient on‑device inference
  • Supports mixed 4x/16x visual token compression

Limits

  • No text‑only mode
  • Requires 8k context for estimates
  • Uncensored content requires moderation

Best for

  • Mobile on‑device inference
  • Rapid prototyping of vision‑language apps
  • Fine‑tuning with SWIFT or LLaMA‑Factory

Who it’s for. Developers building vision‑language applications on iOS, Android, or HarmonyOS who need a small, efficient model. Researchers wanting to experiment with a 1B MLLM on local hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.6 GB 1.5 GB
Fits Get file →
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q5_K_M0.8 GB 1.7 GB
Fits Get file →
Q6_K0.8 GB 1.7 GB
Fits Get file →
Q8_01.1 GB 2.0 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS (0.64 GB, 1.5 GB memory at 8k context) or Q4_K_M (0.67 GB, 1.6 GB). If 12 GB VRAM is available, Q5_K_M (0.75 GB, 1.7 GB) or Q6_K (0.84 GB, 1.7 GB) provide better quality. For maximum quality on 16 GB VRAM, Q8_0 (1.08 GB, 2 GB) is recommended.

What GPU do you need for Sakura MiniCPM V 4.7 1B Uncensored?

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 Uncensored quant should you choose?

Q4_K_M is the usual starting point for Sakura MiniCPM V 4.7 1B Uncensored: 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

Architectureqwen35
Parameters1.01B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bywebmp3
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)3,246
Last updated2026-10-17

Frequently asked questions about Sakura MiniCPM V 4.7 1B Uncensored

How much VRAM does Sakura MiniCPM V 4.7 1B Uncensored 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 Uncensored 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 Uncensored 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 Uncensored 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 Uncensored GGUF?

The files are on Hugging Face in the webmp3/Sakura-MiniCPM-V-4.7-1B-Uncensored-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 Uncensored 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 IQ4_XS or Q4_K_M quantizations fit within 8 GB VRAM with an estimated 1.5–1.6 GB memory usage at 8k context.

Does this model support text‑only inference?

No, the model is designed for vision‑language tasks and does not provide a text‑only mode.

What license applies to this model?

The model is released under the apache-2.0 license, allowing free use with attribution.

Other GGUFs of MiniCPM-V-4.7-1B

Similar models

Browse all →

More from webmp3

All by webmp3 →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →