Product Models Benchmarks Docs Releases Request preview access GitHub
Architectures

Qwen2

Grouped-query attention with qkv bias. The architecture behind the Qwen2 and Qwen2.5 families.

Language 3 supported combinations Apple Silicon
Families

Model families on this architecture

A family names one architecture. Support is declared per model and per target, so the same architecture can be open on one backend and absent from another.

Variants

Every supported combination

ModelCommandCheckpoint on diskVeizik device memoryContextHardware
Qwen2.5-0.5B0.5b942 MiB327 MiB32,768Apple Silicon
Qwen2.5-1.5B1.5b2,944 MiB883 MiB32,768Apple Silicon
Qwen2.5-7B7b14,525 MiB3,923 MiB32,768Apple Silicon

Veizik prepares supported weights in memory; no converted checkpoint is written to disk.

Elsewhere

Related