MI

MiniCPM V Apps

MiniCPMGGUF by tc-mbUpdated 2026-10-27
Download on Hugging Face
Parameters912M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

MiniCPM V Apps 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 6 quants, from 0.5 GB (Q4_K_M) to 3.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

MiniCPM V Apps: 1B‑parameter multimodal model with vision support

MiniCPM V Apps is a 1 billion‑parameter model based on the qwen35 architecture. It supports vision tasks and is distributed in several GGUF quantizations. The model was trained on a context of 262,144 tokens.

Good at

  • Vision‑enabled language tasks
  • Multimodal inference
  • Small‑parameter footprint

Limits

  • No explicit license information
  • No vision support beyond basic image input
  • Large context requires significant VRAM

Best for

  • Image captioning with limited GPU
  • Small‑scale multimodal chatbots
  • Rapid prototyping of vision‑language apps

Who it’s for. Developers needing a lightweight vision‑language model for local deployment. The model is suitable for edge devices with modest GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q4_K_M1.0 GB 1.9 GB
Fits Get file →
—1.7 GB 2.6 GB
Fits Get file →
F161.8 GB 2.7 GB
Fits Get file →
F163.2 GB 4.2 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quantization (0.67 GB file, ~1.6 GB VRAM at 8 k context). If more memory is available, the 1 GB Q4_K_M or 1.66 GB unknown quant offer higher precision. The F16 variants require 2–4 GB VRAM.

What GPU do you need for MiniCPM V Apps?

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 (1.8 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.2 GB file, about 4.2 GB in use).

Which MiniCPM V Apps quant should you choose?

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

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters912M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bytc-mb
FamilyMiniCPM
Downloads (HF)7,624
Last updated2026-10-27

Frequently asked questions about MiniCPM V Apps

How much VRAM does MiniCPM V Apps 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 Apps on an 8 GB GPU?

Yes, with F16: the 3.2 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V Apps GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q4_K_M is 0.7 GB, Q4_K_M is 1.0 GB, file is 1.7 GB, F16 is 1.8 GB, F16 is 3.2 GB.

What context length does MiniCPM V Apps 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 Apps GGUF?

The files are on Hugging Face in the tc-mb/MiniCPM-V-Apps-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 Apps on 8 GB VRAM?

Yes, the Q4_K_M quantization (0.67 GB) uses about 1.6 GB VRAM at 8 k context, fitting within 8 GB.

Does the model support image input?

Yes, MiniCPM V Apps has vision capabilities, enabling image‑based queries.

What quantization gives the best trade‑off?

The 1 GB Q4_K_M quantization balances size and performance, while the 1.66 GB unknown quant offers slightly higher precision.

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →