MA

madlad400 10b mt

MadladGGUF by googleUpdated 2024-04-12
Download on Hugging Face
Parameters10.7B
Context—
Layers—
Architecture—
Smallest quant6.0 GB
Quick answer

madlad400 10b mt needs about 7.3 GB of memory at its main file (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 6.0 GB to 8.8 GB.

Madlad400 10B MT – multilingual translation model

Madlad400 10B MT is a 10.7B parameter multilingual machine translation model. It supports over 400 languages and is based on the T5 architecture. The model is released under the Apache‑2.0 license.

Good at

  • Translation across 400+ languages
  • Large multilingual coverage
  • Competitive performance with larger models

Limits

  • No vision support
  • Requires large VRAM for full precision
  • Not evaluated for production use

Best for

  • Research on multilingual translation
  • Benchmarking translation models
  • Developing multilingual NLP pipelines

Who it’s for. Researchers and developers working on multilingual NLP and machine translation. The model is suitable for academic experiments and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.0 GB 7.3 GB
Tight Get file →
—8.8 GB 10.3 GB
Too big Get file →

For 8‑GB VRAM, use the 6.03‑GB file (est. 7.3 GB memory at 8k context). For 12‑GB VRAM, the 8.79‑GB file (est. 10.3 GB memory at 8k context) is recommended. Memory estimates are approximate.

What GPU do you need for madlad400 10b 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: 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 the main file (6.0 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.8 GB file, about 10.3 GB in use).

Specifications

Architecture from the GGUF header

Parameters10.7B

Source

Quantized bygoogle
FamilyMadlad
Licenseapache-2.0
Downloads (HF)3,405
Last updated2024-04-12

Frequently asked questions about madlad400 10b mt

How much VRAM does madlad400 10b mt need?

About 7.3 GB at its main file with an 8K context window. That is the 6.0 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 madlad400 10b mt on an 8 GB GPU?

Yes, with the smaller files: the 6.0 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of madlad400 10b mt GGUF?

It depends on the quant: file is 6.0 GB, file is 8.8 GB.

Where can I download madlad400 10b mt GGUF?

The files are on Hugging Face in the google/madlad400-10b-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 10b 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 Madlad400 10B MT on 8 GB VRAM?

The 6.03‑GB GGUF file requires about 7.3 GB memory at 8k context, so it can run on 8 GB VRAM with some headroom.

Does the model support vision tasks?

No, the model is purely a language model and does not include vision capabilities.

What license does the model use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from google

All by google →

More Madlad models

All Madlad →

Other medium models

All medium models →