Downloads · 30 days
3
2% of all-time downloads
Qwen3-1.7B-SparseGPT_4_8
MilyaShams/Qwen3-1.7B-SparseGPT_4_8
Qwen3-1.7B-SparseGPT_4_8 is a machine learning model from MilyaShams. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was compressed using the llmcompressor framework.
All-time downloads
144
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
At a glance
- Model type
- qwen3
- Access
- Public
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- b71c06e3
Base models
Model card
From the Hugging Face model README
Compressed Model: MilyaShams/Qwen3-1.7B-SparseGPT_4_8
This model was compressed using the llmcompressor framework.
Compression Details
- Base Model: Qwen/Qwen3-1.7B
- Experiment Name: SparseGPT_4_8
- Recipe / Modifiers Applied:
index=None group=None start=None end=None update=None initialized_=True finalized_=True started_=True ended_=True sparsity=0.5 sparsity_profile=None mask_structure='4:8' owl_m=None owl_lmbda=None sequential_update=False sequential_targets=['Qwen3DecoderLayer'] targets=['Linear'] ignore=[] block_size=128 dampening_frac=0.01 preserve_sparsity_mask=False offload_hessians=False
Note: This model card was automatically generated. All structural modifiers and parameters used during compression are logged above.
- Type
- qwen3
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026