Downloads · 30 days
27
45% of all-time downloads
jbenzaquen/Qwen3.6-35B-A3B-Uncensored-Heretic-QPack
Qwen3.6-35B-A3B-Uncensored-Heretic-QPack is a machine learning model from jbenzaquen. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Swiftlet QPack generated from froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit for use with the Swiftlet runtime and Priv AI.
Downloads · 30 days
27
45% of all-time downloads
All-time downloads
60
Public
Parameters
2.5B
19.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin18.1 GB · 93%
How the weights are stored.
U322.5B · 100%
From the Hugging Face model README
Swiftlet QPack generated from froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit for use with the Swiftlet runtime and Priv AI.
Destination: jbenzaquen/Qwen3.6-35B-A3B-Uncensored-Heretic-QPack
This package preserves the source MLX affine 4-bit, group-size-64 text weights. Swiftlet QPack currently excludes the source checkpoint's vision and MTP tensors.