MA

madlad400 3b mt

MadladGGUF by jbochiUpdated 2024-01-10
Download on Hugging Face
Parameters2.94B
Context—
Layers—
Architecture—
Smallest quant1.0 GB
Quick answer

madlad400 3b mt needs about 1.9 GB of memory at its main file (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.0 GB to 1.7 GB.

MADLAD-400-3B-MT: 3B multilingual translation model

MADLAD-400-3B-MT is a 2.94 billion parameter multilingual translation model based on T5. It supports over 400 languages and is released under Apache‑2.0. The model is available in several GGUF quantizations.

Good at

  • Multilingual translation
  • Large language coverage
  • T5‑style architecture

Limits

  • No vision support
  • No domain‑specific fine‑tuning
  • Requires 8 k context for memory estimates

Best for

  • Research on multilingual NLP
  • Low‑resource language translation
  • Benchmarking translation models

Who it’s for. Researchers and developers needing a compact multilingual translation model. The model is suitable for academic experiments and prototyping but is not intended for production use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 1.6 GB
Fits Get file →
—1.3 GB 1.9 GB
Fits Get file →
—1.7 GB 2.4 GB
Fits Get file →

For 8 GB VRAM use the 1.26 GB quantized file (est. 1.9 GB memory). With 12 GB VRAM the 1.65 GB file (est. 2.4 GB memory) is recommended. The 0.97 GB file (est. 1.6 GB memory) fits 4 GB VRAM but may be slower.

What GPU do you need for madlad400 3b mt?

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 the main file (1.7 GB file, about 2.4 GB in use).

Which madlad400 3b mt quant should you choose?

If memory is tight, the smallest file is the first one in the table at 1.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters2.94B

Source

Quantized byjbochi
FamilyMadlad
Licenseapache-2.0
Downloads (HF)3,467
Last updated2024-01-10

Frequently asked questions about madlad400 3b mt

How much VRAM does madlad400 3b mt need?

About 1.9 GB at its main file with an 8K context window. That is the 1.3 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 madlad400 3b mt on an 8 GB GPU?

Yes, with the smaller files: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of madlad400 3b mt GGUF?

It depends on the quant: file is 1.0 GB, file is 1.3 GB, file is 1.7 GB.

Where can I download madlad400 3b mt GGUF?

The files are on Hugging Face in the jbochi/madlad400-3b-mt repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does madlad400 3b mt 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 MADLAD-400-3B-MT on 8 GB VRAM?

Yes, the 1.26 GB quantized file uses about 1.9 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

No, MADLAD-400-3B-MT is a language model only.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from jbochi

All by jbochi →

More Madlad models

All Madlad →

Other tiny models

All tiny models →