mmnga/DeepSeek-R1-Distill-Llama-70B-gguf

Quantization vs deepseek-ai/DeepSeek-R1-Distill-Llama-70B. mmnga/DeepSeek-R1-Distill-Llama-70B-gguf is a GGUF quantization (Q8_0) of the same weights: 161 tensors match exactly and 562 within quantization error.

Tensors changed: Embeddings 0/1, Attention 0/320, MLP 0/240, Norms 0/161, lm_head 0/1

On the Hub · Downloads on Model Pulse