Downloads · 30 days
6
26% of all-time downloads
SparseGPTQ-Qwen3-8B-Base-uns70-int4
smk2295/SparseGPTQ-Qwen3-8B-Base-uns70-int4
SparseGPTQ-Qwen3-8B-Base-uns70-int4 is a machine learning model from smk2295. 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 other.
Baseline compressed checkpoint for compression research.
All-time downloads
23
Public
Parameters
8.2B
16.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.8 GB · 100%
At a glance
- License
- other
- Model type
- qwen3
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- 72daee18
Model card
From the Hugging Face model README
SparseGPT+GPTQ — Qwen3-8B-Base (70% unstructured sparsity + INT4, symmetric)
Baseline compressed checkpoint for compression research.
- Method: SparseGPT (pruning) + GPTQ (quantization)
- Sparsity: 70% unstructured
- Quantization: INT4, per-group 128, symmetric
- Base: Qwen/Qwen3-8B-Base
Files
model-*.safetensors(sharded): sparse + fake-quantized weights in fp16.compression/scales.safetensors: per-group-128 scales[out, in/128]per layer (keys without.weightsuffix).compression/zeros.safetensors: zero points (constant for symmetric).compression_config.json: method / sparsity / bits / granularity / symmetric.
Notes
- Mask recoverable as
weight == 0. Symmetric per-group-128.
- Type
- qwen3
- License
- other
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026