tensorblock/llm4decompile-1.3b-GGUF
Quantization vs arise-sustech/llm4decompile-1.3b. tensorblock/llm4decompile-1.3b-GGUF is a GGUF quantization (Q2_K) of the same weights: 49 tensors match exactly and 170 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96