MI

MiniCPM V 4

MiniCPMGGUF by second-stateUpdated 2025-08-28
Download on Hugging Face
Parameters3.61B
Context32K
Layers32
Architecturellama
Smallest quant1.4 GB
Quick answer

MiniCPM V 4 needs about 3.0 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 1.4 GB (Q2_K) to 7.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

MiniCPM V 4 – 3.61B parameter multimodal model

MiniCPM V 4 is a 3.61 billion parameter multimodal model built on the MiniCPM family. It supports coding and vision tasks and is available in multiple GGUF quantizations. The model can be run with llama.cpp, Ollama, vLLM, and other local inference engines.

Good at

  • Coding tasks
  • Image and video understanding
  • Multimodal inference

Limits

  • No license specified
  • No official vision support in GGUF
  • Large VRAM required for higher quants

Best for

  • Local multimodal inference
  • Rapid prototyping of vision models
  • Embedded device deployment

Who it’s for. Developers and researchers who need a compact multimodal model for local deployment. The model is suitable for on-device inference and rapid experimentation with coding and vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 2.2 GB
Fits Get file →
Q3_K_S1.6 GB 2.4 GB
Fits Get file →
Q3_K_M1.8 GB 2.6 GB
Fits Get file →
Q3_K_L1.9 GB 2.7 GB
Fits Get file →
Q4_02.1 GB 2.8 GB
Fits Get file →
Q4_K_S2.1 GB 2.9 GB
Fits Get file →
Q4_K_M2.2 GB 3.0 GB
Fits Get file →
Q5_02.5 GB 3.3 GB
Fits Get file →
Q5_K_S2.5 GB 3.3 GB
Fits Get file →
Q5_K_M2.6 GB 3.3 GB
Fits Get file →
Q6_K3.0 GB 3.7 GB
Fits Get file →
Q8_03.8 GB 4.6 GB
Fits Get file →
F167.2 GB 8.0 GB
Tight Get file →

For 8 GB VRAM, Q4_K_M (2.19 GB file, ~3 GB memory at 8 k context) is a good balance. If 12 GB VRAM is available, Q5_K_M (2.56 GB file, ~3.3 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (2.96 GB file, ~3.7 GB memory) or Q8_0 (3.83 GB file, ~4.6 GB memory) can be used.

What GPU do you need for MiniCPM V 4?

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 Q6_K (3.0 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (7.2 GB file, about 8.0 GB in use).

Which MiniCPM V 4 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 4: it balances file size and quality well. Here it is a 2.2 GB file.

The Q8_0 file is 3.8 GB, about 1.8 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 Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.61B
Layers32
Trained context32,768 tokens
KV cache (fp16)32 KB per token

Source

Quantized bysecond-state
FamilyMiniCPM
Downloads (HF)549
Last updated2025-08-28

Frequently asked questions about MiniCPM V 4

How much VRAM does MiniCPM V 4 need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 2.2 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 on an 8 GB GPU?

Yes, with F16: the 7.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 4 GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.6 GB, Q3_K_M is 1.8 GB, Q3_K_L is 1.9 GB, Q4_0 is 2.1 GB, Q4_K_S is 2.1 GB and 7 more.

What context length does MiniCPM V 4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download MiniCPM V 4 GGUF?

The files are on Hugging Face in the second-state/MiniCPM-V-4-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 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 3 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does the GGUF version support vision tasks?

The GGUF quantizations do not include official vision support; the model’s vision capabilities are limited in this format.

What is the maximum context length for this model?

The model supports a context length of 32768 tokens.

Other GGUFs of MiniCPM-V-4

Similar models

Browse all →

More from second-state

All by second-state →

More MiniCPM models

All MiniCPM →

Other small models

All small models →