bartowski/DeepSeek-V2-Chat-0628-GGUF
Quantization vs deepseek-ai/DeepSeek-V2-Chat-0628. bartowski/DeepSeek-V2-Chat-0628-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 300 tensors match exactly and 482 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/241, lm_head 0/1, Attention 0/300, MLP 0/239