Run on your Mac

Run Outlier Plus on Mac Studio M1 Ultra

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

What does Outlier Plus run like on Mac Studio M1 Ultra?

The pairing under examination is Outlier Plus (209 GB MLX 4-bit, Qwen3.5-397B-A17B base, 32K default context, 64 GB unified memory minimum) on a Mac Studio M1 Ultra (Apple M1 Ultra, 20 CPU cores, 48-64 GPU cores, 64|128 GB unified memory, 800 GB/s, 2022). 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 Studio M1 Ultra scales as the ratio 800 / 800 = 1.00× the published M1 Ultra number.

How much memory does the model take during generation?

Outlier’s Outlier Plus has a measured peak generation footprint of about 14.04 GB. The Mac Studio M1 Ultra base configuration ships with 64|128 GB unified, and the rule of thumb is to leave roughly 4 GB for the OS and one open browser tab. Measured throughput on this exact machine: 1.59 tok/s (M1 Ultra 64 GB, 5-rep median, 4096 prefill + 256 generate, mlx_lm 0.31.3, MLX 4-bit). Source: FINAL_LAUNCH_NUMBERS.md.

What is the install path on Mac Studio M1 Ultra for Outlier Plus?

The 2022 Mac Studio M1 Ultra ships with 64|128 GB of unified memory, so headroom for the 64 GB Outlier Plus 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 M1 Ultra machine is that the 209 GB pull from mlx-community/Qwen3.5-397B-A17B-4bit over HTTPS lands in ~/Library/Application Support/Outlier/models/plus/ and download time is bandwidth-limited by the network, not by the 20-core Apple M1 Ultra CPU.

What context window can I use on a 64 GB Mac?

The Outlier Plus 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 64|128 GB Mac Studio M1 Ultra, the default context is the safe starting point.

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

• The Mac Studio M1 Ultra (Apple M1 Ultra, 800 GB/s) is bandwidth-bound on dense 4-bit decode; the throughput ceiling for Outlier Plus on this exact machine is approximately 800 divided by 209 GB tokens per second.
• The Mac Studio M1 Ultra chassis dissipates heat well; sustained decode at the Outlier Plus tier did not show thermal throttling in our 2026-05 internal soak.
• Cold boot of Outlier on a 20-core Apple M1 Ultra 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 Plus on Mac Studio M1 Ultra?

209 GB on disk against 64|128 GB unified memory means the weights alone consume about 327% of the base SKU’s RAM on the Mac Studio M1 Ultra.

Should I pick a different tier?

For lighter-weight work on this Apple M1 Ultra, the Code tier is the next step down and runs visibly faster. The unified-memory explainer works the bandwidth math out, and the bandwidth ratio for Mac Studio M1 Ultra is 1.00× M1 Ultra reference.

Download Outlier for Mac

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