mradermacher/SmolMoE-4x360M-Instruct-GGUF

Same weights, converted vs Fu01978/SmolMoE-4x360M-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 96 new tensors.

Tensors changed: Embeddings 0/1, other 0/32, Norms 0/65, Attention 0/128

On the Hub · Downloads on Model Pulse