mradermacher/Mixtral-4x3B-v1-GGUF
Same weights, converted vs TheDrummer/Mixtral-4x3B-v1. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 90 new tensors.
Tensors changed: other 0/30, Embeddings 0/1, Norms 0/61, Attention 0/120
Same weights, converted vs TheDrummer/Mixtral-4x3B-v1. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 90 new tensors.
Tensors changed: other 0/30, Embeddings 0/1, Norms 0/61, Attention 0/120