mradermacher/locus-gemma-4-e2b-GGUF

Same weights, converted (fewer layers) vs juiceb0xc0de/locus-gemma-4-e2b. mradermacher/locus-gemma-4-e2b-GGUF matches part of juiceb0xc0de/locus-gemma-4-e2b (623 of its 1418 tensors; the rest of juiceb0xc0de/locus-gemma-4-e2b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

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

On the Hub · Downloads on Model Pulse