Ling-3.0-tiny-oQ4e

☆ Save

by TheWirelessPhoenix mlx

165 downloads 0 likes on Hugging Face updated 2026-09-02

Model card

Ling-3.0-tiny-oQ4e

This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.

Quantization details

Model type: bailing_hybrid
Bits: 4
Group size: 64
Format: MLX safetensors

Get this model

hp get TheWirelessPhoenix/Ling-3.0-tiny-oQ4e

The huggingpeers CLI is not released yet. Once it ships, the command above will download the model. Until then, download the weights from Hugging Face.

Details

HuggingPeers ID: ID hpm-cos3BEWYeS8
Provider: Hugging Face
Revision: eefee062847d
Organization: TheWirelessPhoenix
Library: mlx
Parameters: 7.9B
Published: 2026-09-02

Files 12

Total size: 4.3 GiB
LFS files: 2
Parameters: 7.9B
Revision: eefee062847d

Browse files & hashes →

Code

GitHub · jundot/omlx ↗

Linked from the model card — we do not mirror source repositories.

Sources

Hugging Face · TheWirelessPhoenix/Ling-3.0-tiny-oQ4e (this)

View on Hugging Face ↗