mradermacher/Ministral-3-8B-Nymphaea-RP-GGUF

Same weights, converted (fewer layers) vs 0xA50C1A1/Ministral-3-8B-Nymphaea-RP. mradermacher/Ministral-3-8B-Nymphaea-RP-GGUF matches part of 0xA50C1A1/Ministral-3-8B-Nymphaea-RP (309 of its 531 tensors; the rest of 0xA50C1A1/Ministral-3-8B-Nymphaea-RP has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse