APEX Quants (GGUF) Collection MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 17 items • Updated about 3 hours ago • 22
REAM Collection Compressed MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz. • 9 items • Updated 4 days ago • 4
cyankiwi/MiniMax-M2.5-REAP-139B-A10B-AWQ-4bit Text Generation • 23B • Updated 28 days ago • 1.3k • 12
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 134