VI

Vikhrmodels Mini cpm vikhr

VikhrmodelsGGUF by RichardErkhovUpdated 2024-11-12
Download on Hugging Face
Parameters2.78B
Context2K
Layers40
Architectureminicpm
Smallest quant1.3 GB
Quick answer

Vikhrmodels Mini cpm vikhr needs about 5.4 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 19 quants, from 1.3 GB (Q2_K) to 3.0 GB (Q8_0).

Vikhrmodels Mini cpm vikhr is a 2.78B-parameter Vikhrmodels model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 19 quant files, from 1.3 GB (Q2_K) to 3.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 2.5 GB
Fits Get file →
Q3_K_S1.4 GB 2.7 GB
Fits Get file →
Q3_K1.5 GB 2.8 GB
Fits Get file →
Q3_K_M1.5 GB 2.8 GB
Fits Get file →
IQ4_XS1.6 GB 2.9 GB
Fits Get file →
Q3_K_L1.6 GB 2.9 GB
Fits Get file →
Q4_01.7 GB 2.9 GB
Fits Get file →
IQ4_NL1.7 GB 2.9 GB
Fits Get file →
Q4_K_S1.7 GB 3.0 GB
Fits Get file →
Q4_11.8 GB 3.1 GB
Fits Get file →
Q4_K1.9 GB 3.1 GB
Fits Get file →
Q4_K_M1.9 GB 3.1 GB
Fits Get file →
Q5_02.0 GB 3.2 GB
Fits Get file →
Q5_K_S2.0 GB 3.3 GB
Fits Get file →
Q5_K2.1 GB 3.3 GB
Fits Get file →
Q5_K_M2.1 GB 3.3 GB
Fits Get file →
Q5_12.1 GB 3.4 GB
Fits Get file →
Q6_K2.4 GB 3.7 GB
Fits Get file →
Q8_03.0 GB 4.2 GB
Fits Get file →

What GPU do you need for Vikhrmodels Mini cpm vikhr?

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 Q6_K (2.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.5 GB in use).

Which Vikhrmodels Mini cpm vikhr quant should you choose?

Q4_K_M is the usual starting point for Vikhrmodels Mini cpm vikhr: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.0 GB, about 1.6 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 1.3 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

Architectureminicpm
Parameters2.78B
Layers40
Trained context2,048 tokens
KV cache (fp16)360 KB per token

Source

Quantized byRichardErkhov
Licenseapache-2.0
Downloads (HF)120
Last updated2024-11-12

Frequently asked questions about Vikhrmodels Mini cpm vikhr

How much VRAM does Vikhrmodels Mini cpm vikhr need?

About 5.4 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Vikhrmodels Mini cpm vikhr on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vikhrmodels Mini cpm vikhr GGUF?

It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.4 GB, Q3_K is 1.5 GB, Q3_K_M is 1.5 GB, IQ4_XS is 1.6 GB, Q3_K_L is 1.6 GB and 13 more.

What context length does Vikhrmodels Mini cpm vikhr support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.0 GB at 8K and 0.8 GB at 2K.

Where can I download Vikhrmodels Mini cpm vikhr GGUF?

The files are on Hugging Face in the RichardErkhov/Vikhrmodels_-_Mini-cpm-vikhr-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 Vikhrmodels Mini cpm vikhr 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Vikhrmodels models

All Vikhrmodels →

Other tiny models

All tiny models →