Pandas-style transforms on a small dataframe. The hosted LLM APIs category answers this with a remote model; Outlier answers it with the on-device Lite tier. This page is the side-by-side specifically for data cleaning workloads.
Outlier Pro: $49 once · Black Friday price, all of November: $24.50 once, until 30 November
Free to start (Nano and Lite). macOS 15+, Apple silicon. Refund window: 30 days, no questions asked.
For data cleaning, the deciding axis between Outlier and hosted LLM APIs is the data path. Pay-per-token APIs hosted by the model vendor. Outlier holds the prompt and response for data cleaning on the Mac and delivers tokens at the local memory bandwidth of the chip; on the recommended Lite tier, that means working out of the on-disk checkpoint without a network round-trip per turn.
Network round-trip every prompt. For a data cleaning workflow against hosted LLM APIs, the practical consequences are tail-latency variance (the network adds unbounded variance per turn) and the data cleaning prompts leaving your Mac on every request. Outlier’s chat path on the Lite tier issues no outbound HTTPS once the model is on disk, and your chats, files and prompts never leave the Mac. The app does go online for a few other things: the one-time 5.04 GB tier download from Hugging Face, the update check, the price shown when an upgrade window opens and, on Pro, the licence check. Web search goes out only if you turn it on (Pro).
If you are coming from hosted LLM APIs for data cleaning, the right starting point on Outlier is the Lite tier: 5.04 GB on disk, sitting at the quality-vs-speed inflection point for data cleaning; hosted LLM APIs users typically want what they had plus privacy; the Lite tier is the closest match for that without giving up answer quality. Heavier work moves up to the higher tiers in the same app; the Quick tier is not the pick for agent-driven work on data cleaning, because it produced no patch in any of 50 tries on a blind SWE-bench Verified sample.
Moving a data cleaning workflow from hosted LLM APIs to Outlier is a one-time DMG install plus a 5.04 GB pull for the Lite tier. Outlier has no sign-in step, no per-token meter, and no rate-limit page to redirect through. The data cleaning loop after install is open-prompt to local-decode.
For a data cleaning workload moving off hosted LLM APIs onto the Lite tier: Lite sits on a 9B base, a step up in reasoning and code over Nano while still fitting a 16 GB Mac. The MLX explainer has the per-tier breakdown if you want to see how it compares with hosted LLM APIs. The measured accuracy figures are on the tier benchmarks page (MMLU for every tier but Plus; HumanEval for Core and Vision 3.8 only), and for data cleaning specifically: HumanEval covers self-contained functions, which is a fair proxy for the small transforms this work is made of (it was run on Core and Vision 3.8 only).
Pandas-style work is interactive: try a transform, inspect, refine. Local decode keeps the loop tight; round-trip variance drops.
Outlier’s local-only chat path has no sign-in, no auth token and no metered usage: the data cleaning workflow runs against the on-disk Lite tier, no token leaves the device.
This page positions Outlier as an alternative to hosted LLM APIs for data cleaning workflows, not as a drop-in replacement. Specific product surfaces in the hosted LLM APIs category (IDE-integrated suggestions, web-based shared sessions, team-managed prompt libraries) are out of scope for the local app loop and we do not claim equivalence for those when data cleaning is part of a larger team workflow.
For data cleaning: one network round-trip per prompt with hosted LLM APIs versus zero round-trips with Outlier on the Lite tier: the difference is unbounded latency variance against bandwidth-bound, repeatable local throughput.
Download Outlier for MacOn your phone?
Free · M1 or newer · macOS 15+ (free update) · 276 MB. Intel Macs are not supported.
Outlier Pro: $49 once · Black Friday price, all of November: $24.50 once, until 30 November
Refund window: 30 days, no questions asked.
Open weights ship constantly and most are not worth your disk. When one beats a tier Outlier already has, on hardware you already own, we say so and what it replaces. That is the only reason we email.
Your address and which site you sent it from. No IP, no user agent, no referer. Nothing is sent until you press the button. Privacy.
Outlier runs entirely on your Mac. No prompts leave the device. macOS 15+ on Apple Silicon (arm64). Apache 2.0 model weights. Back to home.
Made by Kerr & Company