How much VRAM does the Apple M2 Max (96GB) have?

The Apple M2 Max (96GB) has 96 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).

What is the Apple M2 Max (96GB) best for?

With 96 GB of VRAM, the Apple M2 Max (96GB) is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.

What LLMs can the Apple M2 Max (96GB) run locally?

The Apple M2 Max (96GB) can run 57 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.

Can the Apple M2 Max (96GB) run Llama 3.3 70B Instruct?

Yes. The Apple M2 Max (96GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 5.7 tokens per second.

Can the Apple M2 Max (96GB) run Qwen 3.6 27B?

Yes. The Apple M2 Max (96GB) runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 7.4 tokens per second.

Can the Apple M2 Max (96GB) run Llama 3.1 8B Instruct?

Yes. The Apple M2 Max (96GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 12.5 tokens per second.

Apple M2 Max (96GB)

The Apple M2 Max (96GB) has 96 GB VRAM and 400 GB/s memory bandwidth. It can run 57 of our 70 tracked models natively in VRAM at 8k context.

With 96 GB LPDDR5, the Apple M2 Max (96GB) is a laptop-tier GPU that can run 57 models natively. It handles 70B-class models at Q4 quantization.

Apple M2 Max (96GB): 96GB LPDDR5 at 400 GB/s. 12-core CPU (8P+4E).

32B at Q4 native. 70B at Q3-Q4. ~10-15 t/s for 32B.

Full MLX and llama.cpp support.

Vendor	Apple
Architecture	Apple M2 Max
CPU cores	12 (8P + 4E)
VRAM	96 GB (unified)
Memory type	LPDDR5
Memory bandwidth	400 GB/s
Compute backend	METAL
Tier	Laptop
Released	2023
Models (native)	57 / 70
Models (offload)	0 / 70

Software: MLX gives the best performance on Apple Silicon; llama.cpp Metal backend is a solid alternative. Both are well-supported by Ollama.

Popular models for this GPU

Qwen3 235B-A22B (MoE)MiniMax M2.5 229B MiniMax M2.7 229B Mixtral 8x22B Instruct v0.1 Qwen 3.5 122B-A10B (MoE)

Models this GPU runs natively in VRAM (57)

Too large for this GPU (13)

Compare Apple M2 Max (96GB) with other GPUs

Apple M2 Max (96GB)vsApple M3 Max (128GB)-32 GB VRAM

Frequently asked questions

How much VRAM does the Apple M2 Max (96GB) have?: The Apple M2 Max (96GB) has 96 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M2 Max (96GB) best for?: With 96 GB of VRAM, the Apple M2 Max (96GB) is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.
What LLMs can the Apple M2 Max (96GB) run locally?: The Apple M2 Max (96GB) can run 57 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
Can the Apple M2 Max (96GB) run Llama 3.3 70B Instruct?: Yes. The Apple M2 Max (96GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 5.7 tokens per second.
Can the Apple M2 Max (96GB) run Qwen 3.6 27B?: Yes. The Apple M2 Max (96GB) runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 7.4 tokens per second.
Can the Apple M2 Max (96GB) run Llama 3.1 8B Instruct?: Yes. The Apple M2 Max (96GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 12.5 tokens per second.