← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

mlx-dspark

github.com

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.

DesktopOpen source

Visit github.comexternal siteGitHub736 starsexternal site

Install and connect

From the official MCP Registry, Homebrew, npm, PyPI, and crates.io. Matched by repository or domain once a day.

Reactions (1)

Similar products

by description similarity

  1. dflash-mlx

    Lossless DFlash speculative decoding for MLX on Apple Silicon

    GitHub793 starsgithub.comOpen sourcelatest reaction

  2. Apple MLX

    An array framework for machine learning on Apple silicon

    Product Hunt129 votespypi.orgLibrarylatest reaction

  3. DeepSeek-v4-Flash-DSpark-2x-DGX-Spark

    DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks

    GitHub1,513 starsgithub.comOpen sourcelatest reaction

  4. Rapid-MLX

    Run local LLMs on Mac, 2-3x faster than alternatives

    Hacker News9 ptsGitHub4,119 starsgithub.comDesktopOpen source2 reactionslatest reaction

  5. Bonsai 1.7B ternary model at 442T/s on M4 Max

    A drop-in optimized inference build of Bonsai 1.7B for Apple Silicon. ~42% faster decode (tg128) and ~9% faster prefill (pp512) on M-series GPUs. All Metal kernels written and tuned by ata, our autonomous engineering agent.

    Hacker News13 ptsagents2agents.ailatest reaction