IsValorum/llama.cpp-clover-moe
Updated • 18 • 1
Prebuilt llama.cpp runtime and GGUF files for Diffuspace/Clover-35B-A3B-Preview.
Note Prebuilt llama.cpp with clover_moe support (PR #31306)
Note BF16 GGUF conversion
Note Q8_0 quantization
Note VAL 1.25M I-Matrix, Q8_0 source, Flash Attention