hiratagoh/llm-jp-4-32b-a3b-thinking-GGUF

Same weights, converted vs llm-jp/llm-jp-4-32b-a3b-thinking. Same weights stored in another dtype (BF16 → BF16/F32), plus 96 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/32, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse