dicksondickson/granite-4.2-3b-oQ5e-bf16-MLX

Source: 🤗mit3.7B params7.3 GBsafetensors✓ 1 checksumupdated 17d ago

or submit a torrent

dicksondickson/granite-4.2-3b-oQ5e-bf16-MLX

[!NOTE] Updated Oct 18, 2026: Re-quantized with oMLX 0.7.1.dev1 with improved oQe Quantization. Please re-download if you have an earlier copy.

This model is a quantization of: https://huggingface.co/ibm-granite/granite-4.2-3b

This checkpoint was quantized using oMLX 0.7.1.dev1 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

2Checksums1 awaiting witness

3TorrentNot listed

4SwarmNot checked

Source revision: 267bd9ff2993…
Witnessed: Not yet
Weight files: 1
Model size: 7.3 GB
Downloads · last month: 68
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/granite-4.2-3b-oQ5e-bf16-MLX ./model-folder