robolamp/Ministral-3-8B-Base-2512-GGUF

Same weights, converted (fewer layers) vs mistralai/Ministral-3-8B-Base-2512. robolamp/Ministral-3-8B-Base-2512-GGUF matches part of mistralai/Ministral-3-8B-Base-2512 (309 of its 531 tensors; the rest of mistralai/Ministral-3-8B-Base-2512 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136, lm_head 0/1

On the Hub · Downloads on Model Pulse