Local AI, no more waiting on your Mac.
omlx.ai Source★ 2,579Apache-2.0AI Models & Agents / Model Training & Inference Infrastructure
- Monthly visits
- 148.1K
- Down11.1%MoMSep 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Free
- No monthly subscription pricing
- Launched
- 3mo ago
- 2026-08-30 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- Many people asked which multi-Mac mode to use in oMLX, so I made this image. Two high-end Macs of the same class (e.g. 2x M5 Ultra) -> Use TP (Tensor Parallel). Each Mac runs half of every layer, so prefill and decode both get faster. Data
@jundotkim · 2026-11-05 · 134 likes · 9 reposts · 11.3K views
- oMLX 0.7.4.dev1 is out! https://github.com/jundot/omlx/releases/tag/v0.7.4.dev1 With the new Prefill Accelerator, connect an M5 Max to your big Mac and prefill up to 2.9x faster! Prefill Accelerator (64K prompt, M3 Ultra 512GB + M5 Max 128
@jundotkim · 2026-11-04 · 461 likes · 54 reposts · 104.5K views
- oMLX 0.7.3 is out! https://github.com/jundot/omlx/releases/tag/v0.7.3 Ask AI, the question bar for your local models in any app, now talks back. Press Option-Shift-Space, speak, and your model answers out loud with captions. It can also se
@jundotkim · 2026-10-31 · 231 likes · 14 reposts · 8,770 views
oMLX releases v0.8.0rc1 with NVIDIA GPU prefill accelerationProduct Activity
oMLX released version v0.8.0rc1, introducing support for using NVIDIA GPUs or DGX Spark as a prefill accelerator alongside a Mac holding the model. The update also includes concurrent request priority and faster Affine KV decoding.
Nov 12 · 3d agoLaunch PostX Post
oMLX launched on Product HuntLaunch
Mac LLM server that cuts agent wait times from 90s to 5s
Aug 30 · 3mo agoSource
At the time: 127.5K visits/moVisits: next 2 mo +16%
Open Source & Agent Ecosystem
- GitHub Stars
- ★ 2,579
- Forks
- 237
- License
- Apache-2.0
- Primary language
- Python
Agent, MCP & Developer Integration
Agent Skill- Ecosystem & integrations:
- Claude CodeOpenClawCursorHugging FaceLM StudioClaude
Traffic sources
Traffic breakdown
Channels
- Organic Search45%
- Direct37%
- Social9%
- Referrals7%
- Other2%
Countries
- China22%
- Taiwan11%
- United States11%
- Singapore9%
- Germany8%
Search
Domain authority —Domain registered 2025-09-25
| Keyword | Monthly volume |
|---|---|
| omlx | 26.8K |
| olmx | 2,320 |
| omlx enable web search | 290 |
| omlx install for mac | 240 |
| omlx benchmark | 190 |
Traffic data: Vaneform
Pricing
Website does not list public plan prices.
Trial: None · Observed 2026-11-03 · Source page
Pages & changes
Key pages
Weekly snapshotsChanges
No pricing, plan, or positioning changes detected since tracking started.
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
“Local AI, no more waiting on your Mac.”
Headline Over Large Product Shot hero structure paired with download app / install extension CTA and user count, rating, or key metrics.
Conversion path: Headline Over Large Product Shot + Product UI Screenshot / Component → Download App / Install Extension · Trust bar: User Count, Rating, or Key Metrics
- Outcome & Speed Promise
- Large Hero Product Shot
- Metrics Strip
Palette · click to copy
- Typography
- 8.0
- Color & Contrast
- 7.0
- Layout & Spacing
- 8.0
- Craft & Polish
- 8.0
- Distinctiveness
- 6.0
Structure
- Fonts
- Inter
- Hero layout
- Headline Over Large Product Shot
- Primary visual
- Product UI Screenshot / Component
- Conversion CTA
- Download App / Install Extension
- Social proof
- User Count, Rating, or Key Metrics
- Navigation
- Full-Width Top Bar
- Theme & density
- Light · Airy
- Corners & depth
- Large Radius · 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: #f6f6f7;
--foreground: #111111;
--muted-foreground: #6b6b6b;
--accent: #111111;
--radius: 16px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
}
```
Color area ratio: Background #FFFFFF (~62%) · Surface #F6F6F7 (~16%) · Text #111111 (~10%) · Muted Text #6B6B6B (~7%) · Accent #111111 (~5%). 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: Large Radius; use elevation shadows to separate layers
- Primary visual medium: Product UI Screenshot / Component
- Conversion CTA: Download App / Install Extension · Trust bar uses User Count, Rating, or Key Metrics
- Headline hook: Outcome & Speed Promise
- Hero components: Large Hero Product Shot, Metrics Strip
- Spatial layout notes: Headline Over Large Product Shot hero structure paired with download app / install extension CTA and user count, rating, or key metrics.
- 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 oMLX get?
- Vaneform estimates 148.1K website visits in 2026-09. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
- What is oMLX and what platforms does it support?
- oMLX is catalogued under Model Training & Inference Infrastructure: Local AI, no more waiting on your Mac.. Supported platforms: Web.
- Is oMLX open source?
- oMLX has a public repository (https://github.com/jundot/omlx) under the Apache-2.0 license, recording 2,579 GitHub stars.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 | 9.4M | Undisclosed |
| Groq®Groq was built for this. | — | 3.6M | Undisclosed |
| BytePlusAI Film Award 2027 Powered By BytePlus | — | 3M | Undisclosed |
| ModelScopeFast-forwarding AI development with open-source community. | — | 2.9M | Undisclosed |
| RunpodExperiment, train, fine-tune, deploy, scale on one platform | — | 2.8M | Undisclosed |
| LM StudioThe agent for your computer | $20/mo | 2.5M | Undisclosed |