canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP
Quantization vs deepseek-ai/DeepSeek-V4-Flash. canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP is a quantized version of the other (I32/BF16).
1 other repos hold byte-for-byte identical weight files.
Quantization vs deepseek-ai/DeepSeek-V4-Flash. canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP is a quantized version of the other (I32/BF16).
1 other repos hold byte-for-byte identical weight files.