Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8,…
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
Tags
Similar apps
More in this categoryThe fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs.
2.6kPythonApache-2.0macOSDesktopRun 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…
453SwiftMITmacOSDesktopRapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool…
4kPythonmacOSDesktopHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon.
1.6kPythonApache-2.0macOSDesktopYour iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
920PythonMITmacOSDesktopiOSPersistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection.
158TypeScriptApache-2.0
