A private AI that lives on your Mac
mlxserve.com Source★ 84Apache-2.0 App StoreAI Models & Agents / Model Training & Inference Infrastructure
- Monthly visits
- 19.4K
- Up242.2%MoMSep 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Free
- No monthly subscription pricing
- Launched
- 4mo ago
- 2026-07-03 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- This is crazy, a local model running on my Mac Studio... 🤯 ...100% Local, @deepseek_ai iQ-MLX-3.0bpw + MLX-Serve + @pidotdev + @threejs
@ddalcu · 2026-11-05 · 91 likes · 7 reposts · 5,929 views
- Results from the GSQ-RCO port to MLX-Serve.
@ddalcu · 2026-11-03 · 28 likes · 0 reposts · 1,965 views
- https://mlxserve.com/blog/ship-score/ 回复原帖 @ddalcu: How much ram, how fast, and did it build what I asked ? Decode / Prefill / KLD / Top-1.... who cares. https://x.com/i/article/2117467096657395713
@ddalcu · 2026-11-03 · 2 likes · 0 reposts · 434 views
MLX-Serve 26.11.2 releasedProduct Activity
MLX-Serve released version 26.11.2, introducing multiple options to run Deepseek models from approximately 80GB to 512GB RAM, along with RDMA integration for lossless quant, M3 speedups, and support for various quantization formats.
Nov 6 · 8d agoLaunch PostX Post
MLX-Serve teases support for running Deepseek sub 128GB RAMProduct Activity
MLX-Serve announced upcoming options to run Deepseek sub 128GB RAM, including an upcoming pruned iQ-MLX DS4 pack designed to run on a 96GB M5U.
Nov 5 · 9d agoBuild in PublicX Post
mlx-serve launched on Product HuntLaunch
Local AI on Apple Silicon: LLMs, image/video gen, agents
Jul 7 · 4mo agoSource
mlx-serve launched on Show HN (3 pts)Launch
Mlx-serve – LLM inference server for Apple Silicon, written in Zig
Jul 3 · 4mo agoSource
Open Source & Agent Ecosystem
- GitHub Stars
- ★ 84
- Forks
- 3
- License
- Apache-2.0
- Primary language
- Go
- Ecosystem & integrations:
- RaycastObsidianEnchantedOpen WebUIClaude CodeTelegramHugging FaceClaude
- Exposed tool capabilities:
- Local InferenceImage and music generation
Store data
- Rating
- Rating not syncedRating count not synced
- New ratings last mo
- —
- Price & IAP
- FreeIAP data not synced
- Current version
- —Store metadata
Store assets, rating histograms, install tiers, and screenshots are synced from Apple App Store, Google Play, and Chrome Web Store.
Traffic sources
Traffic breakdown
Channels
- Direct34%
- Organic Search29%
- Social26%
- Referrals5%
- Other5%
Countries
- South Korea98%
- Thailand2%
Search
Domain authority —Domain registered 2026-06-13
| Keyword | Monthly volume |
|---|---|
| mlx serve | 1,100 |
| mlx-serve | 1,080 |
| mlxserve | 560 |
| mlxcore | 310 |
| animatediff image to video workflow no comfyui | 140 |
Traffic data: Vaneform
Pricing
Website does not list public plan prices.
Trial: None · Observed 2026-11-01 · Source page
Pages & changes
Key pages
Weekly snapshots- Homemlxserve.com/
- Featuresmlxserve.com/onboarding/ Snapshot 2026-11-01
Design
Minimal Monochrome (Light canvas, airy density) featuring headline over large product shot layout and product ui screenshot / component visuals.
First-screen preview · click to zoom
First-screen pitch & conversion flow
“A private AI that lives on your Mac”
Headline Over Large Product Shot hero structure paired with download app / install extension CTA and no explicit trust bar.
Conversion path: Headline Over Large Product Shot + Product UI Screenshot / Component → Download App / Install Extension
- Category Positioning Anchor
- Large Hero Product Shot
Palette · click to copy
- Typography
- 8.0
- Color & Contrast
- 8.0
- Layout & Spacing
- 8.0
- Craft & Polish
- 8.0
- Distinctiveness
- 6.0
Structure
- Fonts
- Inter / SF Mono
- Hero layout
- Headline Over Large Product Shot
- Primary visual
- Product UI Screenshot / Component
- Conversion CTA
- Download App / Install Extension
- Social proof
- No Explicit Trust Bar
- Navigation
- Full-Width Top Bar
- Theme & density
- Light · Airy
- Corners & depth
- Pill · With shadow
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Minimal Monochrome
Monochrome palette with a single accent color, hairline dividers, and generous whitespace.
## Design Tokens
```css
:root {
--background: #ffffff;
--surface: #222325;
--foreground: #1d1d1f;
--muted-foreground: #777779;
--accent: #0071e3;
--radius: 9999px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-mono: "SF Mono", ui-monospace, monospace;
}
```
Color area ratio: Background #FFFFFF (~71%) · Surface #222325 (~13%) · Text #1D1D1F (~7%) · Muted Text #777779 (~6%) · Accent #0071E3 (~3%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.
## Layout & Conversion Structure
- Hero layout: Headline Over Large Product Shot
- Navigation: Full-Width Top Bar
- Theme & density: Light · Airy
- Border radius & elevation: Pill; use elevation shadows to separate layers
- Primary visual medium: Product UI Screenshot / Component
- Conversion CTA: Download App / Install Extension
- Headline hook: Category Positioning Anchor
- Hero components: Large Hero Product Shot
- Spatial layout notes: Headline Over Large Product Shot hero structure paired with download app / install extension CTA and no explicit trust bar.
- Visual summary: Minimal Monochrome (Light canvas, airy density) featuring headline over large product shot layout and product ui screenshot / component visuals.
## Avoid
- Multi-stop neon gradients
- Heavy drop shadows
- More than one competing accent color
Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.
Questions & evidence
- How much website traffic does mlx-serve get?
- Vaneform estimates 19.4K website visits in 2026-09. Visits can include repeat visits; this estimate does not measure paying customers or revenue.Source
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.
| Product | Entry price | Visits | Revenue |
|---|---|---|---|
| OllamaGiantMost popular way to build with open models. | $20/mo | 9M | Undisclosed |
| BytePlusAI Film Award 2027 Powered By BytePlus | — | 4.3M | Undisclosed |
| Agent Router统一的 大模型接口网关 | — | 3.8M | Undisclosed |
| Groq®Groq was built for this. | — | 3.6M | Undisclosed |
| ModelScopeFast-forwarding AI development with open-source community. | — | 2.9M | Undisclosed |
| RunpodExperiment, train, fine-tune, deploy, scale on one platform | — | 2.8M | Undisclosed |