MI

MiniCPM V 2 6

MiniCPMGGUF by AI-EngineUpdated 2024-10-17
Download on Hugging Face
Parameters7.61B
Context32K
Layers28
Architectureqwen2
Smallest quant3.0 GB
Quick answer

MiniCPM V 2 6 needs about 6.4 GB of memory at Q5_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 3.0 GB (Q2_K) to 30.5 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

MiniCPM V 2 6 is a 7.61B-parameter MiniCPM model in GGUF format, quantized by AI-Engine. Its trained context length is 32K tokens. The repository has 4 quant files, from 3.0 GB (Q2_K) to 30.5 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 4.0 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
F3230.5 GB 31.4 GB
Too big Get file →

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: the best quant that fits is Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q2_K (3.0 GB file, about 4.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 32 GB VRAM: the best quant that fits is F32 (30.5 GB file, about 31.4 GB in use).

Which MiniCPM V 2 6 quant should you choose?

Q5_K_M (5.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K at 3.0 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

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

Source

Quantized byAI-Engine
FamilyMiniCPM
Licenseother
Downloads (HF)193
Last updated2024-10-17

Frequently asked questions about MiniCPM V 2 6

How much VRAM does MiniCPM V 2 6 need?

About 6.4 GB at Q5_K_M with an 8K context window. That is the 5.4 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 Q5_K_M: the 5.4 GB file needs about 6.4 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: Q2_K is 3.0 GB, Q5_K_M is 5.4 GB, Q8_0 is 8.1 GB, F32 is 30.5 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 AI-Engine/MiniCPM-V-2_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 2 6 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of MiniCPM-V-2_6

Similar models

Browse all →

More from AI-Engine

All by AI-Engine →

More MiniCPM models

All MiniCPM →

Other small models

All small models →