mradermacher/megatron-gpt2-345m-i1-GGUF
Quantization vs robowaifudev/megatron-gpt2-345m. mradermacher/megatron-gpt2-345m-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 195 tensors match exactly and 1 within quantization error.
Tensors changed: Attention 0/48, Norms 0/98, MLP 0/48, Embeddings 0/2