Veizik for Apple Silicon — 2026.10.02-r6.1
A fix release over r6: the CUDA option-forwarding overflow r6 listed as a known issue is fixed, and `veizik keys` now names the file and the reason when it cannot create its lock instead of reporting that another keys command is running.
This page records the state as of 2026-10-05 and is not updated as the catalogue moves. For what runs now, see models.
What this build does
Models in this release
| Model | Task | Context | Status |
|---|---|---|---|
| Qwen2.5-0.5B | Language | 32,768 | Available |
| Qwen2.5-1.5B | Language | 32,768 | Available |
| Qwen2.5-7B | Language | 32,768 | Available |
| Qwen3-1.7B | Language | 32,768 | Available |
| Qwen2.5-0.5B-Instruct | Language | 32,768 | Available |
| Qwen2.5-1.5B-Instruct | Language | 32,768 | Available |
| Qwen2.5-7B-Instruct | Language | 32,768 | Available |
| Qwen3-1.7B-Base | Language | 32,768 | Available |
- Platform
- macOS on Apple Silicon (arm64)
- Install size
- 16.3 MB, 124 files — no dependency to install first
- Verification
- The file name, size and SHA-256 are printed on this page and on the release page, and the two agree. The disk image is signed with a Developer ID and notarised, and carries SHA256SUMS covering its other 49 files, so `shasum -a 256 -c SHA256SUMS` checks the contents after you open it.
- File
- veizik-metal-2026.10.02-r6.1.dmg
- Size
- 6,025,679 bytes
- SHA-256
- 40c619a349f2fd2967b2bf6f7c9c8652a8b2009ea9810c1734039c22aca38ddc
Verify, install, check
$ shasum -a 256 -c SHA256SUMS $ ./install.sh $ veizik doctor
Full steps are in the documentation.
Fixed issues
- CUDA bundles: more than about 64 KB of options forwarded by `veizik run` to a CUDA bundle could overflow a buffer inside your own `veizik` process on Arm builds. It was never reachable from an Apple Silicon install, and x86_64 Linux was not affected.
- `veizik keys` under a fresh home directory: it creates its cache folder, and when it cannot create its lock file it names the file and the reason rather than reporting that another keys command is running.
Known issues in 2026.10.02-r6.1
- `/v1/embeddings` answers 501 in this release.
- The serve window is 4,096 tokens per request for every model in this release (prompt plus max_tokens); `veizik run` is not limited this way.
- Qwen3-1.7B returns its reasoning text inside the answer; add `/no_think` to the prompt for a direct reply.
- Offline use: the session key lasts 48 hours after an online start; restarting the Mac ends that window.
- Not supported: Intel Macs, Windows, Linux. Headless activation is not included in this build.