MI

MiniCPM V 2.6

MiniCPMGGUF by EricZhang1412Updated 2025-05-23
Download on Hugging Face
Parameters7.61B
Context32K
Layers28
Architectureqwen2
Smallest quant4.7 GB
Quick answer

MiniCPM V 2.6 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.7 GB (Q4_K_M) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

MiniCPM V 2.6 – 7.61B parameter model with vision support

MiniCPM V 2.6 is a 7.61‑billion‑parameter model based on the qwen2 architecture. It supports vision tasks and is released under the Apache‑2.0 license. The model was trained with a context length of 32768 tokens.

Good at

  • Vision‑enabled text generation
  • Large context handling
  • Open‑source licensing

Limits

  • Requires at least 5.7 GB VRAM for Q4_K_M
  • No support for audio or video
  • No built‑in vision model beyond basic image input

Best for

  • Chatbots needing image context
  • Research on multimodal LLMs
  • Prototyping with limited GPU memory

Who it’s for. Developers and researchers who need a lightweight, vision‑capable LLM for experimentation or deployment on modest hardware. The model is suitable for open‑source projects and academic use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
F1615.2 GB 16.2 GB
Too big Get file →

For 8 GB VRAM use the Q4_K_M quantization (4.68 GB file, ~5.7 GB memory at 8 k context). If more memory is available, the F16 quantization (15.23 GB file, ~16.2 GB memory) provides higher precision.

What GPU do you need for MiniCPM V 2.6?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).

Which MiniCPM V 2.6 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM V 2.6: it balances file size and quality well. Here it is a 4.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.61B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byEricZhang1412
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)705
Last updated2025-05-23

Frequently asked questions about MiniCPM V 2.6

How much VRAM does MiniCPM V 2.6 need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 MiniCPM V 2.6 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM V 2.6 GGUF?

It depends on the quant: Q4_K_M is 4.7 GB, F16 is 15.2 GB.

What context length does MiniCPM V 2.6 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download MiniCPM V 2.6 GGUF?

The files are on Hugging Face in the EricZhang1412/MiniCPM-V-2.6 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 2.6 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 2.6 on 8 GB VRAM?

Only the Q4_K_M quantization can fit, using about 5.7 GB of VRAM at 8 k context. The F16 quantization requires more than 16 GB.

Does MiniCPM V 2.6 support vision tasks?

Yes, the model has detected vision abilities and can process image inputs.

What license is MiniCPM V 2.6 released under?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other small models

All small models →