Run on your Mac

Run Outlier Core on Mac mini M4 Pro

Last updated 2026-06-18 · Outlier v1.11.469

What does Outlier Core run like on Mac mini M4 Pro?

The pairing under examination is Outlier Core (15.13 GB MLX 4-bit, Qwen3.6-27B base, 32K default context, 24 GB unified memory minimum) on a Mac mini M4 Pro (Apple M4 Pro, 12-14 CPU cores, 16-20 GPU cores, 24|48|64 GB unified memory, 273 GB/s, 2024). Outlier loads this tier as one mlx_lm process inside the bundled FastAPI sidecar. Apple Silicon decode on dense 4-bit weights is bandwidth-bound, so the ceiling on this exact Mac mini M4 Pro scales as the ratio 273 / 800 = 0.34× the published M1 Ultra number.

How much memory does the model take during generation?

Outlier’s Outlier Core has a measured peak generation footprint of about 16 GB. The Mac mini M4 Pro base configuration ships with 24|48|64 GB unified, and the rule of thumb is to leave roughly 4 GB for the OS and one open browser tab. On Mac mini M4 Pro the Outlier Core bandwidth-scaled estimate is ~7.1 tok/s [estimated from family-bandwidth ratio]; derivation: 20.7 tok/s on M1 Ultra × (273 / 800) bus ratio for the Apple M4 Pro. Treat as a first-order projection — the Outlier Core number on this 2024 machine has not been formally measured.

What is the install path on Mac mini M4 Pro for Outlier Core?

The 2024 Mac mini M4 Pro ships with 24|48|64 GB of unified memory, so headroom for the 24 GB Outlier Core requirement is 0 GB on the base SKU. Step-by-step install instructions live on the install guide; the part that varies for this Apple M4 Pro machine is that the 15.13 GB pull from Outlier-Ai/Outlier-Core-27B-MLX-4bit over HTTPS lands in ~/Library/Application Support/Outlier/models/compact/ and download time is bandwidth-limited by the network, not by the 12-14-core Apple M4 Pro CPU.

What context window can I use on a 24 GB Mac?

The Outlier Core tier defaults to 32K context and caps at 256K. KV cache scales linearly with context length on dense models, so longer contexts trade headroom for capacity. On a 24|48|64 GB Mac mini M4 Pro, the default context is the safe starting point.

What works well on this pairing, and what is still rough?

• The Mac mini M4 Pro (Apple M4 Pro, 273 GB/s) is bandwidth-bound on dense 4-bit decode; the throughput ceiling for Outlier Core on this exact machine is approximately 273 divided by 15.13 GB tokens per second.
• The Apple M4 Pro (273 GB/s, 16-20 GPU cores) is current Apple Store silicon as of 2025; new-purchase tok-per-second-per-dollar is best in the lineup at the Outlier Core tier.
• Cold boot of Outlier on a 12-14-core Apple M4 Pro is roughly 50 seconds while the bundled Python.framework warms; this is documented on the v1.9 backlog under the boot-time investigation thread.

What is the unique number for Outlier Core on Mac mini M4 Pro?

15.13 GB on disk against 24|48|64 GB unified memory means the weights alone consume about 63% of the base SKU’s RAM on the Mac mini M4 Pro.

Should I pick a different tier?

For lighter-weight work on this Apple M4 Pro, the Lite tier is the next step down and runs visibly faster. For heavier work, the Code or Vision tier is the next step up; check that the 24|48|64 GB SKU you have can fit its weights before installing. The unified-memory explainer works the bandwidth math out, and the bandwidth ratio for Mac mini M4 Pro is 0.34× M1 Ultra reference.

Download Outlier for Mac

Requires Apple Silicon (M1, M2, M3, or M4) — Intel Macs are not supported. macOS 12+.