Ling-3.0-tiny-oQ4e-fp16

This model was quantized using oQ (oMLX v0.7.1.dev2) mixed-precision quantization.

The effective average is 4.700 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format	Logical weights	Share of total	Tensor storage	Effective bits/weight
Affine 4-bit, group 64	7.455B	94.442%	3.905 GiB	4.50
Affine 5-bit, group 64	0.007B	0.090%	0.005 GiB	5.50
Affine 6-bit, group 64	0.079B	0.999%	0.060 GiB	6.50
Affine 8-bit, group 64	0.352B	4.462%	0.348 GiB	8.50
FP16	0.001B	0.007%	0.001 GiB	16.00
FP32	0.000B	0.000%	0.000 GiB	32.00
Total	7.893B	100%	4.319 GiB	4.700

Storage Breakdown

Component	Logical weights	Storage
Language model	7.893B	4.638 GB / 4.319 GiB
Total	7.893B	4.638 GB / 4.319 GiB