Piccolo-9B-oQ6e

This model was quantized using oQ (oMLX v0.7.4.dev1) mixed-precision quantization.

The effective average is 7.151 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 6-bit, group 64 8.061B 85.668% 6.100 GiB 6.50
Affine 8-bit, group 64 0.892B 9.475% 0.882 GiB 8.50
BF16 0.457B 4.857% 0.851 GiB 16.00
Total 9.410B 100% 7.833 GiB 7.151

Storage Breakdown

Component Logical weights Storage
Language model 8.954B 7.499 GB / 6.984 GiB
Vision 0.456B 0.912 GB / 0.849 GiB
Total 9.410B 8.411 GB / 7.833 GiB
Downloads last month
60
Safetensors
Model size
9B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

6-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for b2z/Piccolo-9B-oQ6e

Finetuned
Qwen/Qwen3.5-9B
Quantized
(7)
this model