Trendingby GlyphMLX
Apple's machine learning framework for Apple silicon.
AI product · last in the top 20 on Sep 19 · first seen Aug 28 · peak 19 on Sep 19 · 2 days in the top 20
Days in the top 20
Sat, Sep 19Why now: mizorewww/laya-mlx: Native MLX runtime for Laya typed decision models, 7–14 ms short decisions on M3 Max.Fri, Aug 28Why now: carloslfu/slotstream: Run a 105 GB AI model on a 48 GB Mac. Qwen3.8-Flash-Next (125B mixture of experts) streams its…
| Day | Rank | Score | |
|---|---|---|---|
| Sat, Sep 19Why now: mizorewww/laya-mlx: Native MLX runtime for Laya typed decision models, 7–14 ms short decisions on M3 Max.GitHub 1 | 10 | 19 | GitHub 1 |
| Fri, Aug 28Why now: carloslfu/slotstream: Run a 105 GB AI model on a 48 GB Mac. Qwen3.8-Flash-Next (125B mixture of experts) streams its…GitHub 1 | 18 | 16 | GitHub 1 |
Trend score by day
Dots are days in the top 20; a ringed dot is a day at number one.
What carried it
mizorewww/laya-mlx: Native MLX runtime for Laya typed decision models, 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.5,981 starscarloslfu/slotstream: Run a 105 GB AI model on a 48 GB Mac. Qwen3.8-Flash-Next (125B mixture of experts) streams its experts from SSD through a slot cache.391 stars
About
Where it was mentioned
- GitHub2 mentions
Named alongside
Apple M3 Max, Mac, PyTorch, Qwen3.8 Flash, Python, Ollama, OpenAI