How much VRAM does the Apple M3 Max (36GB) have?

The Apple M3 Max (36GB) has 36 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).

What is the Apple M3 Max (36GB) best for?

With 36 GB of VRAM, the Apple M3 Max (36GB) is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.

What LLMs can the Apple M3 Max (36GB) run locally?

The Apple M3 Max (36GB) can run 47 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q2_K, Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32.

Can the Apple M3 Max (36GB) run Llama 3.3 70B Instruct?

Yes. The Apple M3 Max (36GB) runs Llama 3.3 70B Instruct natively in VRAM at Q2_K quantization, achieving approximately 17.4 tokens per second.

Can the Apple M3 Max (36GB) run Qwen 3.6 27B?

Yes. The Apple M3 Max (36GB) runs Qwen 3.6 27B natively in VRAM at Q6_K quantization, achieving approximately 18.1 tokens per second.

Can the Apple M3 Max (36GB) run Llama 3.1 8B Instruct?

Yes. The Apple M3 Max (36GB) runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 25 tokens per second.

Apple M3 Max (36GB)

The Apple M3 Max (36GB) has 36 GB VRAM and 400 GB/s memory bandwidth. It can run 47 of our 70 tracked models natively in VRAM at 8k context.

With 36 GB LPDDR5, the Apple M3 Max (36GB) is a laptop-tier GPU that can run 47 models natively. It handles 70B-class models at Q4 quantization.

Apple M3 Max (36GB): 36GB at 400 GB/s.

14B at Q4 native. 32B tight.

Same as other M3 Max.

Vendor	Apple
Architecture	Apple M3 Max
CPU cores	16 (12P + 4E)
VRAM	36 GB (unified)
Memory type	LPDDR5
Memory bandwidth	400 GB/s
Compute backend	METAL
Tier	Laptop
Released	2023
Models (native)	47 / 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

Qwen 2.5 72B Instruct Llama 3.3 70B Instruct DeepSeek R1 Distill Llama 70B Llama 3.1 70B Instruct Mixtral 8x7B Instruct v0.1

Models this GPU runs natively in VRAM (47)

Too large for this GPU (23)

Frequently asked questions

How much VRAM does the Apple M3 Max (36GB) have?: The Apple M3 Max (36GB) has 36 GB of LPDDR5 with 400 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M3 Max (36GB) best for?: With 36 GB of VRAM, the Apple M3 Max (36GB) is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
What LLMs can the Apple M3 Max (36GB) run locally?: The Apple M3 Max (36GB) can run 47 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q2_K, Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32.
Can the Apple M3 Max (36GB) run Llama 3.3 70B Instruct?: Yes. The Apple M3 Max (36GB) runs Llama 3.3 70B Instruct natively in VRAM at Q2_K quantization, achieving approximately 17.4 tokens per second.
Can the Apple M3 Max (36GB) run Qwen 3.6 27B?: Yes. The Apple M3 Max (36GB) runs Qwen 3.6 27B natively in VRAM at Q6_K quantization, achieving approximately 18.1 tokens per second.
Can the Apple M3 Max (36GB) run Llama 3.1 8B Instruct?: Yes. The Apple M3 Max (36GB) runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 25 tokens per second.