MaziyarPanahi/Mixtral-8x22B-v0.1-GGUF

Same weights, converted vs v2ray/Mixtral-8x22B-v0.1. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.

Tensors changed: Embeddings 0/1, other 0/56, Attention 0/224, Norms 0/113, lm_head 0/1

On the Hub · Downloads on Model Pulse