mlx-serve
mlx-serve is 2️⃣下载MLX-Serve App（或brew安装）. It is ranked #158 on the Dev Radar, in Backend & APIs, first seen 64 days ago and shared in 15 posts (245.3k views).
What mlx-serve says about itself
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation. - ddalcu/mlx-serve
GitHub - ddalcu/mlx-serve: Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation. · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation mlx-serve Public Sponsor Notifications You must be signed in to change…
What people said about mlx-serve on X
🔥牛逼了！12GB显卡本地跑763B！DeepSeek-V4.1-Flash-1017量化版炸裂登场，前沿质量几乎零损失！ ISTA-DASLab团队发布GSQ-RCO非均匀量化版，Strata引擎原生支持。763B参数MoE大模型最低压到1.75 bpw，在消费级硬件上就能跑！ 核心亮点 🔹极致压缩 + 几乎无损：IQ2_XXS（2.00 bpw，约249GB）在AIME25、GPQA-Diamond、LiveCodeBench v6上100%恢复原始模型分数；IQ1_M（1.75 bpw，约231GB）整体恢复98.7%。 🔹真正本地可行：单张12GB显卡 +…
— @NFT_Chen, 12 days ago · 1.7k likes · see the post
No cloud was used to make this video. 100% Local. It took 1hr, 30steps Minimax+Yue3+M5U. ⭐️ https://github.com/ddalcu/mlx-serve
— @ddalcu, 4 days ago · 385 likes · see the post
💥苹果党码住！只需一台Mac把 DeepSeek-V4.1-Flash 1017 直接干到每秒100+ token！ 在单台M5 Ultra，80核GPU + 256GB上，用mlx-serve把刚发布的DeepSeek-V4.1-Flash-1017跑通 核心亮点： 🔹生成速度稳定102～112 tok/s，峰值冲到136.7 tok/s 🔹Prefill读prompt飙到1770 tok/s 🔹短问题首字约0.5秒，16k长上下文约9秒出字 🔹3-bit量化（iQ-MLX-3.0bpw），token匹配率89.8%，困惑度仅+3.6% 🔹自带DSpark草稿层 + prompt lookup加速，跑coding…
— @NFT_Chen, 13 days ago · 121 likes · see the post
Alternatives to mlx-serve
- context.dev — came out #1 (by a lot)
- Airlock — @WorkOS – how do you deal with agents and permissions? WorkOS built Airlock, the authorization layer for AI agents.…
- Kimi API Platform — Kimi API Platform, providing the 2.8-trillion-parameter Kimi K3 large language model API with a 1M-token context…
- LongCatAI — API 接入、Token 购买、产品反馈，LongCat AI 能力触手可及。
- opencommerce — today we are announcing openrouter for commerce
- Particle — Particle is building a new AI inference layer for open weight models—fast, low-cost, and reliable. Use our API to…
mlx-serve in numbers
- Rank on the Dev Radar: #158 of 9329
- Shared in 15 posts by 5 accounts: @NFT_Chen, @ddalcu, @ashxhart, @Beamsters1
- 245.3k views on those posts
- First seen 64 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Backend & APIs
FAQ
What is mlx-serve?
2️⃣下载MLX-Serve App（或brew安装） It was first shared on X 64 days ago and is ranked #158 on the Dev Radar.
Is mlx-serve free?
It is open source.
Who shared mlx-serve?
5 accounts on X, including @NFT_Chen, @ddalcu, @ashxhart, in 15 posts totalling 245.3k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.7k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 05:32 UTC. Full method.