Calibration-free VQ-256 compression. Transformers, SSMs, hybrids. Beats GPTQ/AWQ quality. Zero calibration data.
EchoLabs
non-profit
AI & ML interests
AI cross compression architecture
Recent Activity
View all activity
models 17
EchoLabs33/Zamba2-7B-Instruct-v2-GGUF
Text Generation • 11B • Updated • 202
EchoLabs33/Zamba2-2.7B-Instruct-v2-GGUF
Text Generation • 4B • Updated • 187
EchoLabs33/Zamba2-1.2B-Instruct-v2-GGUF
Text Generation • 2B • Updated • 200
EchoLabs33/Zamba2-1.2B-Instruct-GGUF
Text Generation • 2B • Updated • 102
EchoLabs33/olmoe-1b-7b-instruct-hxq
Text Generation • Updated • 552
EchoLabs33/mamba2-1.3b-hxq
Text Generation • Updated • 1.29k
EchoLabs33/mamba-130m-hxq
Text Generation • Updated • 1.52k
EchoLabs33/zamba2-7b-instruct-hxq
Text Generation • Updated • 764
EchoLabs33/zamba2-2.7b-instruct-hxq
Text Generation • Updated • 790
EchoLabs33/zamba2-1.2b-hxq
Text Generation • Updated • 1.49k
datasets 0
None public yet