mradermacher/Qwen3.5-9b-Sushi-Coder-GGUF

Same weights, converted vs bigatuna/Qwen3.5-9b-Sushi-Coder. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 24 new tensors.

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

On the Hub · Downloads on Model Pulse