mradermacher/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base-GGUF
Quantization vs ZERO-POINT-AI/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base. mradermacher/MARTHA-LXVIII.21b_QWEN-3.5-3.6_prune_27b-3.6_base-GGUF is a GGUF quantization (Q8_0) of the same weights: 121 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/121, MLP 0/144, Attention 0/48