Helsinki-NLP / translation updated 2 years ago

opus-mt-tc-big-ko-en

- Model Details - Uses - Risks, Limitations and Biases - How to Get Started With the Model - Training - Evaluation - Citation Information - Acknowledgements

Params
210 M
Context
1,024
Downloads 30d
137 K
Likes
16
Commercial use: allowed cc-by-4.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 32 days
▲ 81 K in the last 30 days (146.9%)
149 K50 K
Aug 20Aug 30Sep 10Sep 20

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f16 0.4 GB 1.0 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
MarianMTModel
Parameters
210 M
Tensor type
F16
Context length
1,024
Vocabulary
32,001
Licence
cc-by-4.0
First seen on the Hub
2022-08-12
Training datasets
undisclosed
flores101-devtest (reported)
0.56615
tatoeba-test-v2021-08-07 (reported)
0.58829
Added to our catalog
2026-08-20
Compare with any translation model