facebook / translation updated 2 years ago

mbart-large-50-many-to-many-mmt

Name: mbart-large-50-many-to-many-mmt
Author: facebook

This model is a fine-tuned checkpoint of mBART-large-50. mbart-large-50-many-to-many-mmt is fine-tuned for multilingual machine translation. It was introduced in Multilingual Translation with Extensible Multilingual Pretraining and Finetuning paper.

Params

610 M

Context

1,024

Downloads 30d

80 K

Likes

410

Licence: unknown Not gated SAFETENSORS 53 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

87 K80 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	2.4 GB	3.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: MBartForConditionalGeneration
Parameters: 610 M
Tensor type: F32
Context length: 1,024
Vocabulary: 250,054
First seen on the Hub: 2022-03-02
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

t5-small 24.7 M nllb-200-distilled-600M 1.6 M opus-mt-nl-en 1.2 M vntl-llama3-8b-v2-gguf 774 K opus-mt-en-ru 686 K opus-mt-en-de 653 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB