bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF

Same weights, converted vs deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Attention 0/448, MLP 0/192, Norms 0/129, lm_head 0/1

On the Hub · Downloads on Model Pulse