MI

CrystalMiniCPM

MiniCPMGGUF by CrystalcareaiUpdated 2024-02-03
Download on Hugging Face
Parameters3.01B
Context4K
Layers40
Architecturellama
Smallest quant2.2 GB
Quick answer

CrystalMiniCPM needs about 5.8 GB of memory at Q5_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 6 GB GPU.

CrystalMiniCPM is a 3.01B-parameter MiniCPM model in GGUF format, quantized by Crystalcareai. Its trained context length is 4K tokens. The repository has 1 quant file, from 2.2 GB (Q5_K_M) to 2.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.2 GB 4.2 GB
Fits Get file →

What GPU do you need for CrystalMiniCPM?

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 Q5_K_M (2.2 GB file, about 5.8 GB in use).

Which CrystalMiniCPM quant should you choose?

Q5_K_M (2.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.01B
Layers40
Trained context4,096 tokens
KV cache (fp16)360 KB per token

Source

Quantized byCrystalcareai
FamilyMiniCPM
Downloads (HF)8
Last updated2024-02-03

Frequently asked questions about CrystalMiniCPM

How much VRAM does CrystalMiniCPM need?

About 5.8 GB at Q5_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 CrystalMiniCPM on an 8 GB GPU?

Yes, with Q5_K_M: the 2.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CrystalMiniCPM GGUF?

It depends on the quant: Q5_K_M is 2.2 GB.

What context length does CrystalMiniCPM support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.0 GB at 8K and 1.5 GB at 4K.

Where can I download CrystalMiniCPM GGUF?

The files are on Hugging Face in the Crystalcareai/CrystalMiniCPM-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Crystalcareai

All by Crystalcareai →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →