DI

dill

DillGGUF by JagrutUpdated 2024-12-09
Download on Hugging Face
Parameters137M
Context2K
Layers12
Architecturenomic-bert
Smallest quant0.3 GB
Quick answer

dill needs about 1.1 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

dill is a 137M-parameter Dill model in GGUF format, quantized by Jagrut. Its trained context length is 2K tokens. The repository has 1 quant file, from 0.3 GB (F16) to 0.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →

What GPU do you need for dill?

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 F16 (0.3 GB file, about 1.1 GB in use).

Which dill quant should you choose?

F16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenomic-bert
Parameters137M
Layers12
Trained context2,048 tokens
KV cache (fp16)36 KB per token

Source

Quantized byJagrut
FamilyDill
RepositoryJagrut/dill
Licenseapache-2.0
Downloads (HF)9
Last updated2024-12-09

Frequently asked questions about dill

How much VRAM does dill need?

About 1.1 GB at F16 with an 8K context window. That is the 0.3 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 dill on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of dill GGUF?

It depends on the quant: F16 is 0.3 GB.

What context length does dill support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.

Where can I download dill GGUF?

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

What license does dill 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 →

Other tiny models

All tiny models →