oQe uses an imatrix sensitivity calibration to assign precision selectively, rather than applying a uniform bit-width to every tensor. The generated oq_imatrix_report.json records the resulting quantization allocation.

python run_oqe_conversion.py Ling-3.0-tiny-bf16 --models-dir /path/to/models --oq-level 6.0 --imatrix-samples 128 --imatrix-seq-length 512 --source-repo https://huggingface.co/inclusionAI/Ling-3.0-tiny

Files

model*.safetensors: quantized MLX weights
model.safetensors.index.json: shard index
config.json: model configuration
oq_imatrix_report.json: imatrix calibration and quantization report

djrsystemservices/Ling-3.0-tiny-oQ6e

Ling-3.0-tiny-oQ6e

Source and credit

Conversion

Files

djrsystemservices/
Ling-3.0-tiny-oQ6e