GO

Google CLD3

GoogleGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters—
Context—
Layers—
Architecturelid-cld3
Smallest quant0.0 GB
Quick answer

Google CLD3 needs about 0.5 GB of memory at F16 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Compact language detector for quick text identification

Google CLD3 is a lightweight language detection model originally shipped in Chromium. It is 440 KB at F16 and runs in well under a millisecond per input. The model supports 109 ISO 639‑1 labels and is licensed under Apache‑2.0.

Good at

  • Fast language detection
  • Tiny memory footprint
  • Low CPU latency

Limits

  • No vision support
  • Limited to 109 languages
  • Only F16 quant available

Best for

  • Browser-side language detection
  • Embedded systems
  • Rapid text preprocessing

Who it’s for. Developers needing a small, fast language detector for web or mobile applications. The model is ideal for projects where memory and latency are critical constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.0 GB 0.5 GB
Fits Get file →

The only quant available is F16, which is 0.5 GB at 8 k context. This is the recommended choice for any system with at least 1 GB of RAM. No other quants are provided.

What GPU do you need for Google CLD3?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.0 GB file, about 0.5 GB in use).

Which Google CLD3 quant should you choose?

F16 (0.0 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

Architecturelid-cld3

Source

Quantized bycstr
FamilyGoogle
Repositorycstr/cld3-GGUF
Licenseapache-2.0
Downloads (HF)1,119
Last updated2026-08-02

Frequently asked questions about Google CLD3

How much VRAM does Google CLD3 need?

About 0.5 GB at F16 with an 8K context window. That is the 0.0 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 Google CLD3 on an 8 GB GPU?

Yes, with F16: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Google CLD3 GGUF?

It depends on the quant: F16 is 0.0 GB.

Where can I download Google CLD3 GGUF?

The files are on Hugging Face in the cstr/cld3-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 Google CLD3 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.

Can I run CLD3 on 8 GB VRAM?

Yes. The model requires only 0.5 GB of RAM, well below 8 GB VRAM limits.

Does CLD3 support rare languages?

CLD3 trades raw accuracy on rare languages for a tiny footprint, so it may be less accurate on uncommon languages.

Is CLD3 compatible with other language detection backends?

Yes, its C ABI mirrors lid_fasttext_* and can be routed alongside GlotLID or LID‑176 in CrispASR.

More from cstr

All by cstr →