mradermacher/BigFalcon3-from10B-GGUF
Quantization vs ehristoforu/BigFalcon3-from10B. mradermacher/BigFalcon3-from10B-GGUF is a GGUF quantization (Q8_0) of the same weights: 131 tensors match exactly and 457 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/131, MLP 0/195, Attention 0/260