TheBloke/Marx-3B-v3-GGUF
Quantization vs acrastt/Marx-3B-V3. TheBloke/Marx-3B-v3-GGUF is a GGUF quantization (Q8_0) of the same weights: 130 tensors match exactly and 226 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/130, MLP 0/96, Attention 0/128