Composing zsh and bash one-liners and short scripts. The container-based local model runners category runs open weights on your own hardware, as Outlier does, so the deciding difference for shell scripts is not the data path but the surface around the model: docker- or VM-wrapped local model servers. Outlier answers it with the on-device nano tier and an agent loop. This page is the side-by-side specifically for shell scripts workloads.
For shell scripts, the deciding axis between Outlier and container-based local model runners is the data path. Docker- or VM-wrapped local model servers. Outlier holds the prompt and response for shell scripts on the Mac and delivers tokens at the local memory bandwidth of the chip; on the nano-recommended tier, that means working out of the on-disk checkpoint without a network round-trip per turn.
Local execution, varies by tool. For a shell scripts workflow against container-based local model runners, the prompt stays on the machine on both sides, so neither tail latency nor provider-side logging separates them. Outlier’s chat path on the nano tier issues no outbound HTTPS once the model is on disk; the only network request in the lifecycle is the one-time 2.37 GB tier download from Hugging Face.
If you are coming from container-based local model runners for shell scripts, the right starting point on Outlier is the nano tier — 2.37 GB on disk, sitting at the quality-vs-speed inflection point for shell scripts-shaped prompts. container-based local model runners users typically want what they had plus privacy; the nano 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’s weak code performance rules it out for code-shaped shell scripts.
Moving a shell scripts workflow from container-based local model runners to Outlier is a one-time DMG install plus a 2.37 GB pull for the nano tier. The sign-in step that container-based local model runners typically requires has no equivalent on the Outlier side: there is no account, no per-token meter, and no rate-limit page to redirect through. The shell scripts loop after install is open-prompt to local-decode.
For a shell scripts workload moving off container-based local model runners onto the nano tier: Nano is the smallest tier, tuned over a 4B base; the one formally measured Outlier accuracy number is Nano HumanEval 81.1% (pass@1, full 164-set). Strong fluency for its size. The MLX explainer has the per-tier breakdown if you want to see how it compares with container-based local model runners. The one formally measured Outlier accuracy figure is Nano HumanEval 81.1% (pass@1, full 164-set), and for shell scripts specifically: that figure is measured on the same Nano tier this workload runs on, so it is directly applicable rather than extrapolated.
Shell-script drafting is a Nano-tier task: short context, fast turnaround. The 2.37 GB Nano model fits a 16 GB Air with room to spare.
For shell scripts specifically, container-based local model runners tools share a common operational shape: a sign-in, an auth token bound to that sign-in, some kind of metered usage, and a content policy that applies to the shell scripts prompts you submit. Outlier’s local-only chat path does not surface any of those: the shell scripts workflow runs against the on-disk nano tier, no token leaves the device.
This page positions Outlier as an alternative to container-based local model runners for shell scripts workflows, not as a drop-in replacement. Specific product surfaces in the container-based local model runners 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 shell scripts is part of a larger team workflow.
For shell scripts: one network round-trip per prompt with container-based local model runners versus zero round-trips with Outlier on the nano tier — the difference is unbounded latency variance against bandwidth-bound, repeatable local throughput.
Download Outlier for MacRequires Apple Silicon (M1, M2, M3, or M4) — Intel Macs are not supported. macOS 12+.
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 12+ on Apple Silicon (arm64). Apache 2.0 model weights. Back to home.