Downloads · 30 days
14
44% of all-time downloads
QianheChen01/Hy-MT2-30B-A3B-APEX-Imatrix-I-Quality-MLX
Hy-MT2-30B-A3B-APEX-Imatrix-I-Quality-MLX is a machine learning model from QianheChen01. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Converted locally from alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF/Hy-MT2-30B-A3B-APEX-Imatrix-I-Quality.gguf for oMLX/MLX inference.
Downloads · 30 days
14
44% of all-time downloads
All-time downloads
32
Public
Parameters
5.7B
20.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors20.7 GB · 100%
How the weights are stored.
U324.7B · 83%
From the Hugging Face model README
Converted locally from alphaZimuth/Hy-MT2-30B-A3B-APEX-GGUF/Hy-MT2-30B-A3B-APEX-Imatrix-I-Quality.gguf for oMLX/MLX inference.
The source GGUF mixed precision policy is preserved by mapping IQ4_XS/Q5_K/Q6_K/Q8_0 tensors to MLX affine 4/5/6/8-bit modules with group size 64. Quantization parameters and ordinary floating weights use BF16; expert routing biases remain F32.
Source tensor types: {'F32': 287, 'IQ4_XS': 60, 'Q5_K': 30, 'Q6_K': 272, 'Q8_0': 117}.