mradermacher/TinyMixtral-4x248M-MoE-GGUF

Same weights, converted vs Isotonic/TinyMixtral-4x248M-MoE. Same weights stored in another dtype (F32 → F16/F32), plus 36 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/12, Norms 0/25, Attention 0/48

On the Hub · Downloads on Model Pulse