TensorFold/Qwen3.8-Flash-Next-MLX-oQ4-MTP
Quantization vs Qwen/Qwen3.8-Flash-Next. TensorFold/Qwen3.8-Flash-Next-MLX-oQ4-MTP is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs Qwen/Qwen3.8-Flash-Next. TensorFold/Qwen3.8-Flash-Next-MLX-oQ4-MTP is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.