Repository · GitHub
carloslfu/slotstream
Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.
| Owner | carloslfu |
|---|---|
| License (as declared) | MIT |
| Stars | 477 |
| Forks | 39 |
| Main language | Swift |
| Created | 28 August 2026 |
| Last updated at source | 16 October 2026 |
Stars, last 4 days
477 now (+6 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.