carloslfu/slotstream

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

240 best points · 119 comments · 2 Hacker News posts · 656 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s (240 points, 118 comments, by carloslfu, 2026-09-01)
• Show HN: Slotstream, run Qwen3.8-Flash-Next 4-bit on a low-memory Mac (3 points, 1 comments, by carloslfu, 2026-08-31)