Qwen3
Adds per-head query and key normalisation and drops the qkv bias relative to Qwen2.
Language
1 supported combination
Apple Silicon

Qwen3 on this site
1 supported combination across Apple Silicon.
Image rendered by Veizik for NVIDIA, development build (linux x86_64) · SD3.5-medium · NVIDIA RTX 3090 · Powered by Stability AI
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.
Every supported combination
| Model | Model identifier | Short name | Checkpoint on disk | Veizik device memory | Context | Hardware |
|---|---|---|---|---|---|---|
| Qwen3-1.7B | qwen3-1.7b | 1.7b | 3,281 MiB | 923 MiB | 32,768 | Apple Silicon |
Veizik prepares supported weights in memory; no converted checkpoint is written to disk.