GPU

Apple MacBook Pro M3 Max (30-core GPU) 36GB for local AI

27GB memory, 300 GB/s bandwidth, and deterministic compatibility links for downloadable local models.

VRAM

27GB

Bandwidth

300 GB/s

Architecture

Apple M3 Max

Memory type

LPDDR5 Unified

Models to check on this GPU

• Can it run Hermes-4.3-36B?
• Can it run Intern-S2-Preview?
• Can it run Qwen3.5-35B-A3B?
• Can it run Qwen3.6-35B-A3B?
• Can it run Qwen-AgentWorld-35B-A3B?
• Can it run Nous-Capybara-34B?
• Can it run Qwen3-VL-32B-Instruct?
• Can it run DeepSeek R1 Distill Qwen 32B?