LL

lll

LllGGUF by 1WesleyUpdated 2025-05-18
Download on Hugging Face
Parameters1.72B
Context40K
Layers28
Architectureqwen3
Smallest quant1.8 GB
Quick answer

lll needs about 3.3 GB of memory at Q8_0 (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

lll is a 1.72B-parameter Lll model in GGUF format, quantized by 1Wesley. Its trained context length is 40K tokens. The repository has 1 quant file, from 1.8 GB (Q8_0) to 1.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.8 GB 3.3 GB
Fits Get file →

What GPU do you need for lll?

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 Q8_0 (1.8 GB file, about 3.3 GB in use).

Which lll quant should you choose?

Q8_0 (1.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters1.72B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized by1Wesley
FamilyLll
Repository1Wesley/lll
Licenseapache-2.0
Downloads (HF)8
Last updated2025-05-18

Frequently asked questions about lll

How much VRAM does lll need?

About 3.3 GB at Q8_0 with an 8K context window. That is the 1.8 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 lll on an 8 GB GPU?

Yes, with Q8_0: the 1.8 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of lll GGUF?

It depends on the quant: Q8_0 is 1.8 GB.

What context length does lll support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download lll GGUF?

The files are on Hugging Face in the 1Wesley/lll repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does lll 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 1Wesley

All by 1Wesley →

More Lll models

All Lll →

Other tiny models

All tiny models →