mradermacher/smol_llama-4x220M-MoE-GGUF

Same weights, converted vs Isotonic/smol_llama-4x220M-MoE. Same weights stored in another dtype (BF16 → F16/F32), plus 30 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/10, Norms 0/21, Attention 0/40

On the Hub · Downloads on Model Pulse