tensorblock/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUF
Quantization vs alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B. tensorblock/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 121 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168