mradermacher/GhostShell-4B-i1-GGUF

Quantization (fewer layers) vs DuoNeural/GhostShell-4B. mradermacher/GhostShell-4B-i1-GGUF matches part of DuoNeural/GhostShell-4B (623 of its 1148 tensors; the rest of DuoNeural/GhostShell-4B has no counterpart). On the shared part: mradermacher/GhostShell-4B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 279 tensors match exactly and 344 within quantization error.

Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132

On the Hub · Downloads on Model Pulse