MI

MiniCPM V 4 5

MiniCPMGGUF by openbmbUpdated 2026-08-18
Download on Hugging Face
Parameters8.2B
Context40K
Layers36
Architectureqwen3
Smallest quant4.8 GB
Quick answer

MiniCPM V 4 5 needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 19 quants, from 4.8 GB (Q4_0) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

8B‑parameter vision‑language model with high‑FPS video understanding

MiniCPM‑V 4.5 is an 8.2 B‑parameter model built on Qwen3‑8B and SigLIP2‑400M. It supports coding and vision tasks and offers fast and deep thinking modes. The model can process high‑resolution images and long videos efficiently.

Good at

  • Vision‑language tasks
  • High‑FPS video understanding
  • OCR and document parsing

Limits

  • No vision support beyond images and video
  • Requires large VRAM for full context
  • License not specified

Best for

  • Mobile MLLM inference
  • Video analytics on limited hardware
  • OCR in mobile apps

Who it’s for. Developers building mobile or edge applications that need vision‑language capabilities with limited compute. The model is suitable for users who require fast inference and can switch to deep thinking for complex queries.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.8 GB 6.5 GB
Fits Get file →
Q4_04.8 GB 6.5 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 7.0 GB
Fits Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_05.7 GB 7.4 GB
Tight Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_K_M5.8 GB 7.6 GB
Tight Get file →
Q5_K_M5.8 GB 7.6 GB
Tight Get file →
Q5_16.2 GB 7.9 GB
Tight Get file →
Q5_16.2 GB 7.9 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →
Q8_08.7 GB 10.4 GB
Too big Get file →
Q8_08.7 GB 10.4 GB
Too big Get file →
F1616.4 GB 18.1 GB
Too big Get file →
F1616.4 GB 18.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈6.5 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M or Q5_K_S (≈7–7.6 GB). For 16 GB VRAM, Q5_1 or Q6_K (≈7.9–8.4 GB).

What GPU do you need for MiniCPM V 4 5?

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: the best quant that fits is Q5_1 (6.2 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 GB in use).

Which MiniCPM V 4 5 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4 5: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.7 GB, about 1.7 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 4.8 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

Architectureqwen3
Parameters8.2B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byopenbmb
FamilyMiniCPM
Downloads (HF)42,775
Last updated2026-08-18

Frequently asked questions about MiniCPM V 4 5

How much VRAM does MiniCPM V 4 5 need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 5 on an 8 GB GPU?

Yes, with Q5_1: the 6.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 4 5 GGUF?

It depends on the quant: Q4_0 is 4.8 GB, Q4_0 is 4.8 GB, Q4_K_S is 4.8 GB, Q4_K_M is 5.0 GB, Q4_K_M is 5.0 GB, Q4_1 is 5.2 GB and 13 more.

What context length does MiniCPM V 4 5 support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download MiniCPM V 4 5 GGUF?

The files are on Hugging Face in the openbmb/MiniCPM-V-4_5-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run MiniCPM‑V 4.5 on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantization, which requires about 6.5 GB of VRAM at 8 k context.

Does the model support video input?

Yes, it can process high‑FPS and long videos using a unified 3D‑Resampler.

What is the context length?

The model was trained on 40,960 tokens and supports up to that context length.

Other GGUFs of MiniCPM-V-4_5

Similar models

Browse all →

More from openbmb

All by openbmb →

More MiniCPM models

All MiniCPM →

Other small models

All small models →