CanItRun Logocanitrun.

Apple M3 (8GB)

The Apple M3 (8GB) has 8 GB VRAM and 100 GB/s memory bandwidth. It can run 20 of our 70 tracked models natively in VRAM at 8k context.

With 8 GB LPDDR5, the Apple M3 (8GB) is a laptop-tier GPU that can run 20 models natively. It's best for smaller models under 8B parameters.

Apple M3 (8GB): 8GB at 100 GB/s — base M3.

7B at Q4 tight. ~3-6 t/s for 7B.

8GB is minimum — consider 16GB+.

VendorApple
ArchitectureApple M3
CPU cores8 (4P + 4E)
VRAM8 GB (unified)
Memory typeLPDDR5
Memory bandwidth100 GB/s
Compute backendMETAL
TierLaptop
Released2023
Models (native)20 / 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

Models this GPU runs natively in VRAM (20)

Too large for this GPU (50)

Frequently asked questions

How much VRAM does the Apple M3 (8GB) have?
The Apple M3 (8GB) has 8 GB of LPDDR5 with 100 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M3 (8GB) best for?
With 8 GB of VRAM, the Apple M3 (8GB) is best for running compact models (1B–8B) at low quantization, suitable for edge inference, prototyping, and lightweight tasks.
What LLMs can the Apple M3 (8GB) run locally?
The Apple M3 (8GB) can run 20 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q3_K_M, Llama 3.2 3B Instruct at Q8_0, Llama 3.2 1B Instruct at FP32.
Can the Apple M3 (8GB) run Llama 3.3 70B Instruct?
The Apple M3 (8GB) does not have enough VRAM to run Llama 3.3 70B Instruct. You would need more VRAM or a lower quantization level.
Can the Apple M3 (8GB) run Qwen 3.6 27B?
The Apple M3 (8GB) does not have enough VRAM to run Qwen 3.6 27B. You would need more VRAM or a lower quantization level.
Can the Apple M3 (8GB) run Llama 3.1 8B Instruct?
Yes. The Apple M3 (8GB) runs Llama 3.1 8B Instruct natively in VRAM at Q3_K_M quantization, achieving approximately 29.1 tokens per second.