mradermacher/PLLuM-4B-instruct-2512-GGUF

Same weights, converted (fewer layers) vs CYFRAGOVPL/PLLuM-4B-instruct-2512. mradermacher/PLLuM-4B-instruct-2512-GGUF matches part of CYFRAGOVPL/PLLuM-4B-instruct-2512 (444 of its 883 tensors; the rest of CYFRAGOVPL/PLLuM-4B-instruct-2512 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

On the Hub · Downloads on Model Pulse