mradermacher/mimi_0.6b-GGUF

Same weights, converted vs aifeifei798/mimi_0.6b. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/84

On the Hub · Downloads on Model Pulse