mradermacher/qwen3.5-amharic-4b-thinking-GGUF

Same weights, converted vs abdukuzi45/qwen3.5-amharic-4b-thinking-uncensored. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 39 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

On the Hub · Downloads on Model Pulse