Understanding performance of masks: test?a^6 vs. ?a^6test vs. ?a^6

[penguinkeeper]

It's a known problem with the way that Hashcat distributes work, it uses the first 4 characters to parallelise, so when the first 4 characters has a large keyspace, it can distribute work across the thousands of GPU cores, but when it's only a single candidate - "test", Hashcat really struggles to fully make use of the whole GPU, causing very low speeds as you're seeing there. It's a known, architectural problem with Hashcat that unfortunately can't (and won't) be solved