EnlistedGhost/Pixtral-12B-2409-GGUF

Same weights, converted (fewer layers) vs mistralai/Pixtral-12B-2409. EnlistedGhost/Pixtral-12B-2409-GGUF matches part of mistralai/Pixtral-12B-2409 (363 of its 585 tensors; the rest of mistralai/Pixtral-12B-2409 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

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

On the Hub · Downloads on Model Pulse