ROCmFPX GGUF Quants Collection Hybrid q4/q8 ROCmFPX GGUF quants. Requires the ROCmFPX fork of llama.cpp. • 4 items • Updated about 23 hours ago
ROCmFPX GGUF Quants Collection Hybrid q4/q8 ROCmFPX GGUF quants. Requires the ROCmFPX fork of llama.cpp. • 4 items • Updated about 23 hours ago
Model Mad Science Collection Experimental models with weird architectures. Frankenmerges, layer duplications, expert pruning, expert merging, and whatever else seems worth trying. • 4 items • Updated Mar 17