squeezebits/Llama-3.1-8B-Instruct-FP8-dynamic
8B
•
Updated
•
1
AI & ML interests
SqueezeBits is building an ecosystem for designing, training, and deploying highly compressed Neural Networks.
models
8
squeezebits/Llama-3.1-8B-Instruct-quantized.w4a16
2B
•
Updated
•
19
squeezebits/Llama-3.1-8B-Instruct-quantized.w4a16.per_channel
2B
•
Updated
•
1
squeezebits/kanana-1.5-2.1b-instruct-2505-mlx
Text Generation
•
0.4B
•
Updated
•
4
squeezebits/Qwen3-32B-AWQ
6B
•
Updated
•
3
squeezebits/Qwen3-32B-AWQ-G32
7B
•
Updated
•
6
squeezebits/Qwen-32B-FP8-Dynamic
Text Generation
•
33B
•
Updated
•
6
squeezebits/dummy_slm
Text Generation
•
13.4M
•
Updated
•
325