LE

Lens

LensGGUF by szwagrosUpdated 2026-05-24
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant11.9 GB
Quick answer

Lens needs about 12.8 GB of memory at Q4_K_XL (a 11.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Lens is a 20.9B-parameter Lens model in GGUF format, quantized by szwagros. Its trained context length is 128K tokens. The repository has 1 quant file, from 11.9 GB (Q4_K_XL) to 11.9 GB (Q4_K_XL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_XL11.9 GB 12.8 GB
Too big Get file →

What GPU do you need for Lens?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_XL (11.9 GB file, about 12.8 GB in use).

Which Lens quant should you choose?

Q4_K_XL (11.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byszwagros
FamilyLens
Repositoryszwagros/Lens
Licenseapache-2.0
Downloads (HF)3
Last updated2026-05-24

Frequently asked questions about Lens

How much VRAM does Lens need?

About 12.8 GB at Q4_K_XL with an 8K context window. That is the 11.9 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 Lens on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lens GGUF?

It depends on the quant: Q4_K_XL is 11.9 GB.

What context length does Lens support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Lens GGUF?

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

What license does Lens 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 szwagros

All by szwagros →

More Lens models

All Lens →

Other medium models

All medium models →