Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark…
Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration
Tags
Similar apps
More in this categoryPersonal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).
3.6kTypeScriptApache-2.0The 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-2.0macOSDesktopYour iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
920PythonMITmacOSDesktopiOSmacOS menubar app for fast local DeepSeek V4.1, with 1M context.
916SwiftMITmacOSDesktopUp 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,…
702PythonMITmacOSDesktopRun 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…
453SwiftMITmacOSDesktop
