mradermacher/starcoder2-3b-GGUF
Quantization vs bigcode/starcoder2-3b. mradermacher/starcoder2-3b-GGUF is a GGUF quantization (Q8_0) of the same weights: 302 tensors match exactly and 181 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/122, MLP 0/120, Attention 0/240