soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ
Quantization vs deepseek-ai/deepseek-moe-16b-chat. soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ is a quantized version of the other (I32/BF16).
Quantization vs deepseek-ai/deepseek-moe-16b-chat. soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ is a quantized version of the other (I32/BF16).