MI

MiniCPM V 4_6

MiniCPMGGUF by openbmbUpdated 2026-08-17
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

MiniCPM V 4_6 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.5 GB (Q4_0) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

MiniCPM‑V 4.6 – a compact multimodal LLM for image and video understanding

MiniCPM‑V 4.6 is a 0.752 B parameter model built on Qwen3.5‑0.8B and SigLIP2‑400M. It supports vision tasks and runs efficiently on consumer GPUs. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Vision‑language understanding
  • Efficient inference on mobile GPUs
  • Mixed 4x/16x visual token compression

Limits

  • No text‑only inference without vision
  • Requires at least 8 k context for memory estimates
  • No built‑in vision support in some frameworks

Best for

  • Mobile on‑device image captioning
  • Video summarization on low‑power devices
  • Rapid prototyping of multimodal apps

Who it’s for. Developers building lightweight multimodal applications on iOS, Android, or HarmonyOS. Researchers needing a small, efficient vision‑language model for edge deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_10.5 GB 1.4 GB
Fits Get file →
Q5_00.6 GB 1.5 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q5_10.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, Q4_0 or Q4_K_S (~0.5 GB) provide ~1.4 GB memory usage at 8 k context. For 16 GB VRAM, Q6_K or Q8_0 (~0.63–0.81 GB) give ~1.5–1.7 GB usage. Higher precision F16 (~1.52 GB) needs >2 GB VRAM.

What GPU do you need for MiniCPM V 4_6?

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 F16 (1.5 GB file, about 2.4 GB in use).

Which MiniCPM V 4_6 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4_6: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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 Q4_0 at 0.5 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
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byopenbmb
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)17,948
Last updated2026-08-17

Frequently asked questions about MiniCPM V 4_6

How much VRAM does MiniCPM V 4_6 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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_6 on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 4_6 GGUF?

It depends on the quant: Q4_0 is 0.5 GB, Q4_K_S is 0.5 GB, Q4_K_M is 0.5 GB, Q4_1 is 0.5 GB, Q5_0 is 0.6 GB, Q5_K_S is 0.6 GB and 5 more.

What context length does MiniCPM V 4_6 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_6 GGUF?

The files are on Hugging Face in the openbmb/MiniCPM-V-4.6-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_6 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 4.6 on 8 GB VRAM?

Yes, use Q4_0 or Q4_K_S quantization; memory usage is about 1.4 GB at 8 k context.

Does the model support single‑image and video input?

Yes, it inherits single‑image, multi‑image, and video understanding from the MiniCPM‑V family.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiniCPM-V-4.6

Similar models

Browse all →

More from openbmb

All by openbmb →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →