A hybrid deduplication system operates to detect variable-sized deduplication matches, while performing the storage deduplication on fixed-size segments of data. The hybrid deduplication system calculates unique identifiers for variable-sized sections of data within a data stream being written to a deduplicated data store. The hybrid deduplication system then compares those newly-calculated identifiers to identifiers of variable-sized sections of data that have already been stored within the deduplicated data store. If a match is found, the hybrid deduplication system identifies the location of each of the fixed-size data segment(s), already stored in the deduplicated data store, that include the identified variable-sized section of data. Instead of writing the sections that match already-existing sections to the deduplicated data store, the hybrid deduplication system simply causes the creation of a reference to the identified storage locations, indicating that the data stream being written includes the data in these pre-existing storage locations.