Run Apertus 1.5 8B on M5 Max

Yes — Apertus 1.5 8B (8B) runs at 90 tok/s on M5 Max with 64 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.3s. A capable open-source LLM with 8B parameters.

Speed
90
tok/s
First Token
0.3
seconds
RAM Needed
64
GB minimum
Engine
MLX
recommended
Want to run Apertus 1.5 8B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Apertus 1.5 8B on M5 Max using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second90 tok/s
Time to first token0.3s
QuantizationQ4_K_M
Minimum RAM64 GB
Recommended engineMLX
Parameters8B
Benchmark date2026-08

Q4_K_M 8B MLX M5 Max

Setup Guide: Run Apertus 1.5 8B on M5 Max

The recommended engine for Apertus 1.5 8B on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/apertus-15-8b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run apertus-15-8b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 55 tok/s 0.4s 16 GB Ollama

System Requirements

To run Apertus 1.5 8B on M5 Max you need:

🛒 Get a Mac that runs Apertus 1.5 8B

Apertus 1.5 8B needs about 64 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how Apertus 1.5 8B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard