unsloth/Qwen3.5-9B-Base

Same weights, converted vs Qwen/Qwen3.5-9B-Base. Same weights stored in another dtype (BF16/F32 → BF16).

Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 0/208, Attention 0/332, Norms 0/215

1 derivatives checked

• protocolsyncllc/medgap-qwen-3.5-9b: Full fine-tune

On the Hub · Downloads on Model Pulse