huawei-csl/Qwen3-235B-A22B-3bit-SINQ
Text Generation
•
Updated
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
huawei-csl/Qwen3-32B-4bit-ASINQ
Text Generation
•
18B
•
Updated
•
63
•
8
huawei-csl/Qwen3-32B-4bit-SINQ
Text Generation
•
18B
•
Updated
•
76
•
7
huawei-csl/Qwen3-14B-4bit-ASINQ
Text Generation
•
9B
•
Updated
•
72
•
6
huawei-csl/Qwen3-14B-4bit-SINQ
Text Generation
•
9B
•
Updated
•
37
•
5
huawei-csl/Qwen3-1.7B-4bit-SINQ
Text Generation
•
1B
•
Updated
•
39
•
5
huawei-csl/Qwen3-32B-3bit-ASINQ
Text Generation
•
6B
•
Updated
•
135
•
5
huawei-csl/Qwen3-1.7B-4bit-ASINQ
Text Generation
•
1B
•
Updated
•
47
•
5
huawei-csl/Qwen3-32B-3bit-SINQ
Text Generation
•
6B
•
Updated
•
162
•
5
huawei-csl/Qwen3-14B-3bit-SINQ
Text Generation
•
3B
•
Updated
•
148
•
5
huawei-csl/Qwen3-14B-3bit-ASINQ
Text Generation
•
3B
•
Updated
•
149
•
5
huawei-csl/Qwen3-1.7B-3bit-ASINQ
Text Generation
•
0.5B
•
Updated
•
169
•
6
huawei-csl/Qwen3-1.7B-3bit-SINQ
Text Generation
•
0.5B
•
Updated
•
200
•
7