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 Agents-A1-4B-bf16 --models-dir /path/to/models --oq-level 6.0 --imatrix-samples 128 --imatrix-seq-length 512 --mtp-donor /path/to/Qwen3.5-4B-MTP-donor --mtp-source-repo https://huggingface.co/guru87/Qwen3.5-4B-MTP --source-repo https://huggingface.co/InternScience/Agents-A1-4B

Lightning MTP

The donor checkpoint was merged as an oMLX Lightning MTP head. The donor was kept at its shipped precision and was not independently quantized.

Donor checkpoint: Qwen3.5-4B-MTP-donor
Donor repository / credit: https://huggingface.co/guru87/Qwen3.5-4B-MTP

Files

model.safetensors: quantized MLX weights
model-mtp.safetensors: shipped-precision Lightning MTP head
config.json: model configuration
oq_imatrix_report.json: imatrix calibration and quantization report

djrsystemservices/Agents-A1-4B-oQ6e-mtp

Agents-A1-4B-oQ6e-mtp

Source and credit

Conversion

Lightning MTP

Files

djrsystemservices/
Agents-A1-4B-oQ6e-mtp