mradermacher/medgemma-nuslerp-27b-GGUF
Quantization (fewer layers) vs copiglet/medgemma-nuslerp-27b. mradermacher/medgemma-nuslerp-27b-GGUF matches part of copiglet/medgemma-nuslerp-27b (808 of its 1247 tensors; the rest of copiglet/medgemma-nuslerp-27b has no counterpart). On the shared part: mradermacher/medgemma-nuslerp-27b-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 435 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248