hotchpotch/CAT-Translate-0.8b-mlx-q8

Source: 🤗text-generationmit793M params1.6 GBsafetensors✓ 1 checksumupdated 275d ago

or submit a torrent

CAT-Translate-0.8b MLX q8

This repository provides MLX quantized weights (q8) converted from the original model.

Original model: cyberagent/CAT-Translate-0.8b

Quantization: MLX q8 (8-bit).

CommentsShare your thoughts and shape the future of sovereign AI.

@hotchpotch is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @hotchpotch

Files and sources

✓SourceAvailable on Hugging Face

✓Checksums1 recorded

3TorrentNot listed

4SwarmNot checked

Source revision: a98abbe3c628…
Witnessed: 4 Oct 2026, 06:01 UTC
Weight files: 1
Model size: 1.6 GB
Downloads · last month: 48
Publisher: Unclaimed

View provenance entry #21682 →

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo hotchpotch/CAT-Translate-0.8b-mlx-q8 ./model-folder