How much VRAM does the Apple M3 Max (128GB) have?

The Apple M3 Max (128GB) has 128 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).

What is the Apple M3 Max (128GB) best for?

With 128 GB of VRAM, the Apple M3 Max (128GB) 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 M3 Max (128GB) run locally?

The Apple M3 Max (128GB) can run 61 of the 80 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 M3 Max (128GB) run Llama 3.3 70B Instruct?

Yes. The Apple M3 Max (128GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 4.2 tokens per second.

Can the Apple M3 Max (128GB) run Qwen 3.6 27B?

Yes. The Apple M3 Max (128GB) runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 5.8 tokens per second.

Can the Apple M3 Max (128GB) run Llama 3.1 8B Instruct?

Yes. The Apple M3 Max (128GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 9.7 tokens per second.

Apple M3 Max (128GB)

The Apple M3 Max (128GB) has 128 GB VRAM and 400 GB/s memory bandwidth. It can run 61 of our 80 tracked models natively in VRAM at 8k context.

With 128 GB LPDDR5, the Apple M3 Max (128GB) is a laptop-tier GPU that can run 61 models natively. It handles 70B-class models at Q4 quantization.

Apple M3 Max (128GB): 2023 flagship laptop with 128GB LPDDR5 at 400 GB/s. Up to 40-core GPU.

70B at Q4 ~12-20 t/s. 32B at ~18-28 t/s. Memory bandwidth advantage over M4 Pro.

Mature llama.cpp Metal support. MLX fully compatible. Good used market value.

Vendor	Apple
Architecture	Apple M3 Max
CPU cores	16 (12P + 4E)
VRAM	128 GB (unified)
Memory type	LPDDR5
Memory bandwidth	400 GB/s
Compute backend	METAL
Tier	Laptop
Released	2023
Models (native)	61 / 80
Models (offload)	0 / 80

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 Step 3.7 Flash Step 3.5 Flash

Models this GPU runs natively in VRAM (61)

Too large for this GPU (19)

Compare Apple M3 Max (128GB) with other GPUs

Explore

Browse all guides →Browse all models →Browse all GPUs →

Frequently asked questions

How much VRAM does the Apple M3 Max (128GB) have?: The Apple M3 Max (128GB) has 128 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M3 Max (128GB) best for?: With 128 GB of VRAM, the Apple M3 Max (128GB) 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 M3 Max (128GB) run locally?: The Apple M3 Max (128GB) can run 61 of the 80 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 M3 Max (128GB) run Llama 3.3 70B Instruct?: Yes. The Apple M3 Max (128GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 4.2 tokens per second.
Can the Apple M3 Max (128GB) run Qwen 3.6 27B?: Yes. The Apple M3 Max (128GB) runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 5.8 tokens per second.
Can the Apple M3 Max (128GB) run Llama 3.1 8B Instruct?: Yes. The Apple M3 Max (128GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 9.7 tokens per second.