Run on your Mac

Run Outlier Nano on Mac mini M4

Last updated 2026-11-04

What does Outlier Nano run like on Mac mini M4?

The pairing under examination is Outlier Nano (2.37 GB MLX 4-bit, Qwen3.5-4B base, 8K context on Free (32K on Pro), 6 GB unified memory minimum) on a Mac mini M4 (Apple M4, 10 CPU cores, 10 GPU cores, 16, 24 or 32 GB unified memory, 120 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 figure on this exact Mac mini M4 scales roughly as the ratio 120 / 800 = 0.15× of the published M1 Ultra number.

Does Mac mini M4 hold that speed on a long job?

The Mac mini M4 is a desktop with active cooling, which is the configuration that comes closest to holding the figure above through a sustained back-and-forth session. There is no battery to trade against and no lap to keep cool, so the limit on Outlier Nano here is the 120 GB/s memory bus rather than the thermal envelope. This is the shape of machine to pick if the job runs unattended.

How much memory does the model take during generation?

The tier catalog lists a peak generation footprint of about 3 GB for Outlier Nano, for a short chat; a long agent session needs more. The rule of thumb is to leave roughly 4 GB for the OS and one open browser tab, so across the Mac mini M4 memory options that leaves 16 GB → 9.0 GB free; 24 GB → 17.0 GB free; 32 GB → 25.0 GB free. On Mac mini M4 the Outlier Nano bandwidth-scaled estimate is ~10.8 tok/s [estimated from family-bandwidth ratio]; derivation: 71.7 tok/s on M1 Ultra × (120 / 800) bus ratio for the Apple M4. Treat as a first-order projection, the Outlier Nano number on this 2024 machine has not been formally measured. The only real check of this method, Nano on a 16 GB M4 Air, ran about 3× faster than the 10.8 tok/s it projects, so read the figure as conservative.

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

The 2024 Mac mini M4 ships with 16, 24 or 32 GB of unified memory. Headroom over the 6 GB Outlier Nano minimum is 10 GB on the 16 GB base model. Step-by-step install instructions live on the install guide; the part that varies for this Apple M4 machine is that the 2.37 GB pull from Outlier-Ai/Outlier-Nano-4B-MLX-4bit over HTTPS lands in ~/Library/Application Support/Outlier/models/nano/ and download time is bandwidth-limited by the network, not by the 10-core Apple M4 CPU.

What context window can I use on a 16 GB Mac?

The Outlier Nano tier runs at 8K context on Free; on Pro it defaults to 32K and caps at 128K. KV cache scales linearly with context length on dense models, so longer contexts trade headroom for capacity. On a 16 GB Mac mini M4, the default context is the safe starting point.

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

• The Apple M4 (120 GB/s, 10 GPU cores) was current Apple Store silicon in 2025.
• The first launch of Outlier on a 10-core Apple M4 takes longer while the bundled Python.framework warms; later launches skip that step. I have not timed it.

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

2.37 GB on disk against the 16 GB Mac mini M4 (the smallest configuration that meets the 6 GB minimum) means the weights alone take about 15% of its memory.

Should I pick a different tier?

For heavier work, the Lite tier is the next step up; check that the memory configuration you have (16, 24 or 32 GB on this Mac) can fit its weights before installing. The unified-memory explainer works the bandwidth math out, and the bandwidth ratio for Mac mini M4 is 0.15× M1 Ultra reference.

Download Outlier for Mac

On your phone? Send the Mac link to yourself

Free · M1 or newer · macOS 15+ (free update) · 276 MB. Intel Macs are not supported.