mradermacher/voxel-representation-gemma3-4b-GGUF
Same weights, converted (fewer layers) vs Menlo/voxel-representation-gemma3-4b. mradermacher/voxel-representation-gemma3-4b-GGUF matches part of Menlo/voxel-representation-gemma3-4b (445 of its 884 tensors; the rest of Menlo/voxel-representation-gemma3-4b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1