GPU

Apple MacBook Pro M2 Max (38-core GPU) 96GB for local AI

72GB memory, 400 GB/s bandwidth, and deterministic compatibility links for downloadable local models.

VRAM

72GB

Bandwidth

400 GB/s

Architecture

Apple M2 Max

Memory type

LPDDR5 Unified

Models to check on this GPU

• Can it run OpenAI gpt-oss-120b?
• Can it run GLM-4.5V?
• Can it run GLM-4.6V?
• Can it run Qwen3-Next-80B-A3B-Thinking?
• Can it run Qwen3-Coder-Next?
• Can it run Qwen2.5-VL-72B-Instruct?
• Can it run Qwen2.5-72B-Instruct?
• Can it run Meta Llama 3.3 70B Instruct?