bartowski/Gryphe_Tiamat-24B-Magistral-GGUF

Same weights, converted (fewer layers) vs Gryphe/Tiamat-24B-Magistral. bartowski/Gryphe_Tiamat-24B-Magistral-GGUF matches part of Gryphe/Tiamat-24B-Magistral (363 of its 585 tensors; the rest of Gryphe/Tiamat-24B-Magistral has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse