Qwopus3.8-27B-Coder-Flash-oQ5e-mtp

This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.

The effective average is 5.889 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 5-bit, group 64 24.440B 87.971% 15.648 GiB 5.50
Affine 6-bit, group 64 1.544B 5.558% 1.168 GiB 6.50
Affine 8-bit, group 64 1.282B 4.614% 1.268 GiB 8.50
BF16 0.516B 1.857% 0.961 GiB 16.00
Total 27.781B 100% 19.046 GiB 5.889

Storage Breakdown

Component Logical weights Storage
Language model 26.896B 19.164 GB / 17.848 GiB
Vision 0.461B 0.921 GB / 0.858 GiB
MTP head 0.425B 0.365 GB / 0.340 GiB
Total 27.781B 20.450 GB / 19.046 GiB
Downloads last month
108
Safetensors
Model size
28B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

5-bit

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

Model tree for Estirius/Qwopus3.8-27B-Coder-Flash-oQ5e-mtp

Base model

Qwen/Qwen3.8-27B
Quantized
(20)
this model