VI

Vikhr tiny 0.1 Q4 K M

VikhrGGUF by itlwasUpdated 2024-12-18
Download on Hugging Face
Parameters2.78B
Context2K
Layers40
Architectureminicpm
Smallest quant1.9 GB
Quick answer

Vikhr tiny 0.1 Q4 K M 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.

Vikhr tiny 0.1 Q4 K M is a 2.78B-parameter Vikhr model in GGUF format, quantized by itlwas. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.9 GB (Q4_K_M) to 1.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.9 GB 3.1 GB
Fits Get file →

What GPU do you need for Vikhr tiny 0.1 Q4 K M?

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 (1.9 GB file, about 5.4 GB in use).

Which Vikhr tiny 0.1 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Vikhr tiny 0.1 Q4 K M: it balances file size and quality well. Here it is a 1.9 GB file.

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 byitlwas
FamilyVikhr
Licenseapache-2.0
Downloads (HF)21
Last updated2024-12-18

Frequently asked questions about Vikhr tiny 0.1 Q4 K M

How much VRAM does Vikhr tiny 0.1 Q4 K M 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 Vikhr tiny 0.1 Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 1.9 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vikhr tiny 0.1 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 1.9 GB.

What context length does Vikhr tiny 0.1 Q4 K M 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 Vikhr tiny 0.1 Q4 K M GGUF?

The files are on Hugging Face in the itlwas/Vikhr-tiny-0.1-Q4_K_M-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 Vikhr tiny 0.1 Q4 K M 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.

Other GGUFs of Vikhr-tiny-0.1

Similar models

Browse all →

More from itlwas

All by itlwas →

More Vikhr models

All Vikhr →

Other tiny models

All tiny models →