DevQuasar/nicoboss.Qwen-3-32B-Medical-Reasoning-GGUF

Same weights, converted vs nicoboss/Qwen-3-32B-Medical-Reasoning. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse