mradermacher/snapgate-code-4B-GGUF
Same weights, converted (fewer layers) vs kadalicious22/snapgate-code-4B. mradermacher/snapgate-code-4B-GGUF matches part of kadalicious22/snapgate-code-4B (398 of its 713 tensors; the rest of kadalicious22/snapgate-code-4B has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144