LI

ling3 tr tiny pruned hukuk

LingGGUF by webbrain-oneUpdated 2026-10-20
Download on Hugging Face
Parameters5.29B
Context128K
Layers24
Architecturebailingmoe3
Smallest quant2.9 GB
Quick answer

ling3 tr tiny pruned hukuk needs about 7.8 GB of memory at IQ4_XS (a 2.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 2.9 GB (IQ4_XS) to 3.1 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 17.7 GB.

ling3 tr tiny pruned hukuk is a 5.29B-parameter Ling model in GGUF format, quantized by webbrain-one. Its trained context length is 128K tokens. The repository has 2 quant files, from 2.9 GB (IQ4_XS) to 3.1 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS2.9 GB 7.8 GB
Tight Get file →
IQ4_NL3.1 GB 8.0 GB
Tight Get file →

What GPU do you need for ling3 tr tiny pruned hukuk?

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: the best quant that fits is IQ4_NL (3.1 GB file, about 8.0 GB in use).

Which ling3 tr tiny pruned hukuk quant should you choose?

IQ4_XS (2.9 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

Architecturebailingmoe3
Parameters5.29B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)528 KB per token

Source

Quantized bywebbrain-one
FamilyLing
Licensemit
Downloads (HF)137
Last updated2026-10-20

Frequently asked questions about ling3 tr tiny pruned hukuk

How much VRAM does ling3 tr tiny pruned hukuk need?

About 7.8 GB at IQ4_XS with an 8K context window. That is the 2.9 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 ling3 tr tiny pruned hukuk on an 8 GB GPU?

Yes, with IQ4_NL: the 3.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ling3 tr tiny pruned hukuk GGUF?

It depends on the quant: IQ4_XS is 2.9 GB, IQ4_NL is 3.1 GB.

What context length does ling3 tr tiny pruned hukuk support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.4 GB at 8K and 17.7 GB at 32K.

Where can I download ling3 tr tiny pruned hukuk GGUF?

The files are on Hugging Face in the webbrain-one/ling3-tr-tiny-pruned-hukuk-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 ling3 tr tiny pruned hukuk use?

Hugging Face lists the license as mit. 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 webbrain-one

All by webbrain-one →

More Ling models

All Ling →

Other small models

All small models →