Run on your Mac

Run Outlier Code on MacBook Pro M4 Max

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

What does Outlier Code run like on MacBook Pro M4 Max?

The pairing under examination is Outlier Code (15.13 GB MLX 4-bit, Qwen3.6-27B base, 64K default context, 24 GB unified memory minimum) on a MacBook Pro M4 Max (Apple M4 Max, 14-16 CPU cores, 32-40 GPU cores, 36|48|64|128 GB unified memory, 410-546 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 MacBook Pro M4 Max scales as the ratio 410-546 / 800 = 0.51× the published M1 Ultra number.

How much memory does the model take during generation?

Outlier’s Outlier Code has a measured peak generation footprint of about 16 GB. The MacBook Pro M4 Max base configuration ships with 36|48|64|128 GB unified, and the rule of thumb is to leave roughly 4 GB for the OS and one open browser tab. On MacBook Pro M4 Max the Outlier Code bandwidth-scaled estimate is ~10.6 tok/s [estimated from family-bandwidth ratio]; derivation: 20.7 tok/s on M1 Ultra × (410-546 / 800) bus ratio for the Apple M4 Max. Treat as a first-order projection — the Outlier Code number on this 2024 machine has not been formally measured.

What is the install path on MacBook Pro M4 Max for Outlier Code?

The 2024 MacBook Pro M4 Max ships with 36|48|64|128 GB of unified memory, so headroom for the 24 GB Outlier Code requirement is 12 GB on the base SKU. Step-by-step install instructions live on the install guide; the part that varies for this Apple M4 Max machine is that the 15.13 GB pull from Outlier-Ai/Outlier-Code-27B-MLX-4bit over HTTPS lands in ~/Library/Application Support/Outlier/models/code/ and download time is bandwidth-limited by the network, not by the 14-16-core Apple M4 Max CPU.

What context window can I use on a 36 GB Mac?

The Outlier Code tier defaults to 64K context and caps at 256K. KV cache scales linearly with context length on dense models, so longer contexts trade headroom for capacity. On a 36|48|64|128 GB MacBook Pro M4 Max, the default context is the safe starting point.

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

• The MacBook Pro M4 Max (Apple M4 Max, 410-546 GB/s) is bandwidth-bound on dense 4-bit decode; the throughput ceiling for Outlier Code on this exact machine is approximately 410-546 divided by 15.13 GB tokens per second.
• The Apple M4 Max (410-546 GB/s, 32-40 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 Code tier.
• Cold boot of Outlier on a 14-16-core Apple M4 Max 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 Code on MacBook Pro M4 Max?

15.13 GB on disk against 36|48|64|128 GB unified memory means the weights alone consume about 42% of the base SKU’s RAM on the MacBook Pro M4 Max.

Should I pick a different tier?

For lighter-weight work on this Apple M4 Max, the Compact tier is the next step down and runs visibly faster. For heavier work, the Plus tier is the next step up; check that the 36|48|64|128 GB SKU you have can fit its weights before installing. The unified-memory explainer works the bandwidth math out, and the bandwidth ratio for MacBook Pro M4 Max is 0.51× M1 Ultra reference.

Download Outlier for Mac

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