tensorblock/AMD-Llama-135m-GGUF
Quantization vs amd/AMD-Llama-135m. tensorblock/AMD-Llama-135m-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 25 tensors match exactly and 86 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48