This collection contains the models quantized with the SINQ quantization method.
AI & ML interests
None defined yet.
Recent Activity
Papers
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding
models
19
huawei-csl/Qwen3-Next-80B-A3B-Instruct-4bit-SINQ
Text Generation
•
Updated
•
6
•
2
huawei-csl/Qwen3-Next-80B-A3B-Instruct-3bit-SINQ
Text Generation
•
Updated
•
7
•
2
huawei-csl/Qwen3-32B-3bit-ASINQ
Text Generation
•
6B
•
Updated
•
14
•
5
huawei-csl/Apertus-8B-2509-4bit-SINQ
Text Generation
•
5B
•
Updated
•
8
•
2
huawei-csl/Qwen3-32B-3bit-SINQ
Text Generation
•
6B
•
Updated
•
9
•
6
huawei-csl/Qwen3-1.7B-4bit-SINQ
Text Generation
•
1B
•
Updated
•
8
•
5
huawei-csl/Kimi-Linear-48B-A3B-Instruct-3bit-SINQ
Text Generation
•
7B
•
Updated
•
14
•
1
huawei-csl/Qwen3-1.7B-4bit-ASINQ
Text Generation
•
1B
•
Updated
•
6
•
5
huawei-csl/Qwen3-14B-4bit-SINQ
Text Generation
•
9B
•
Updated
•
17
•
5
huawei-csl/Apertus-8B-2509-4bit-ASINQ
Text Generation
•
5B
•
Updated
•
11
•
2
datasets
0
None public yet