meta-models/Muse-Glimmer-30B-GGUF
Quantization vs meta-models/Muse-Glimmer-30B. meta-models/Muse-Glimmer-30B-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 209 tensors match exactly and 418 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/209, MLP 0/156, Attention 0/260, lm_head 0/1
2 derivatives checked
- RadixArk/Muse-Glimmer-q4k-dynamic-MLX: Quantization
- RadixArk/Muse-Glimmer-q4km-gs128-MLX: Quantization