dicksondickson/FrogNano-4B-2609-oQ4e-mtp-MLX

Source: 🤗mit4.7B params9.3 GBsafetensors✓ 2 checksumsupdated yesterday

or submit a torrent

dicksondickson/FrogNano-4B-2609-oQ4e-mtp-MLX

[!NOTE] Updated Nov 3, 2026: Re-quantized with oMLX 0.7.3 with improved oQe Quantization and Better Low-Bit oQ. Please re-download if you have an earlier copy.

This model is a quantization of: https://huggingface.co/microsoft/FrogNano-4B-2609

This checkpoint was quantized using oMLX 0.7.3 with imatrix enabled.

Important tensors are left at bf16 which is for Apple M3 chips and later.

Run the model using oMLX: https://github.com/jundot/omlx

CommentsShare your thoughts and shape the future of sovereign AI.

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

Files and sources

✓SourceAvailable on Hugging Face

2Checksums2 awaiting witness

3TorrentNot listed

4SwarmNot checked

Source revision: 5d6d5174fc63…
Witnessed: Not yet
Weight files: 2
Model size: 9.3 GB
Downloads · last month: 226
Publisher: Unclaimed

Public checksum record coming on the next sync

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 dicksondickson/FrogNano-4B-2609-oQ4e-mtp-MLX ./model-folder