Downloads · 30 days
5
24% of all-time downloads
JSQ-Qwen3-8B-Base-uns70-int4
smk2295/JSQ-Qwen3-8B-Base-uns70-int4
JSQ-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
21
Public
Parameters
8.2B
16.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.5 GB · 100%
At a glance
- License
- other
- Model type
- qwen3
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- 0ec89eba
Model card
From the Hugging Face model README
JSQ — Qwen3-8B-Base (70% unstructured sparsity + INT4, symmetric)
Baseline compressed checkpoint for compression research.
- Method: JSQ (joint sparsification + quantization, Wanda-style pruning + weight quant)
- Sparsity: 70% unstructured
- Quantization: INT4, per-group 128, symmetric (absmax)
- Base: Qwen/Qwen3-8B-Base
Files
model.safetensors: sparse + fake-quantized weights in fp16, loadable viaAutoModelForCausalLM.compression/scales.safetensors: per-group-128 symmetric scales[out, in/128]per layer (scale=absmax/7).compression_config.json: method / sparsity / bits / granularity / symmetric.
Notes
- Mask recoverable as
weight == 0. Symmetric:w=round(x/scale)*scale, levels in[-7,7].
- Type
- qwen3
- License
- other
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026