A fast, memory-efficient chat model for laptops and edge devices.
Q4_K_M default
tokens
Canonical metadata is separated from immutable version and Run evidence.
Sparrow Chat 3B demonstrates low-memory discovery and confirmed compatibility on machines without a discrete GPU.
2 published Runs; each result links to its exact conditions and evidence level.
Benchmark claims remain tied to immutable revisions even after the repository changes.
Reduced repetition and improved structured extraction.
Explicit model relationships are stored as typed edges rather than inferred from names.
Other models used for chat.
A general-purpose multilingual instruction model with broad runtime support.
