mradermacher/Mixtronix-8B-GGUF
Same weights, converted vs bunnycore/Mixtronix-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160
Same weights, converted vs bunnycore/Mixtronix-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160