mradermacher/Qwen3-1.7B-Sushi-Coder-GGUF
Same weights, converted vs bigatuna/Qwen3-1.7B-Sushi-Coder. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, converted vs bigatuna/Qwen3-1.7B-Sushi-Coder. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112