Written by Jakub Rusinowski · Last updated July 12, 2026
The 3nm upgrade to M2 Pro. Up to 36 GB unified memory at 153 GB/s. 55 t/s on 8B models. Handles Qwen 3 14B and Phi-4 14B comfortably at Q4. 30W total system power in a laptop.
| VRAM | 36 GB unified memory |
| Memory Bandwidth | 153 GB/s |
| TDP | 30 W |
| Architecture | ARM, 3nm TSMC |
| Release Year | 2023 |
| MSRP at Launch | $1,999 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | 9.7–20 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | Does not fit — needs ~44 GB of 27 GB usable |
All models below run comfortably in 36 GB unified memory with Q4_K_M quantization.
| Llama 3.1 Family | Llama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| Llama 3.2 Family | Llama 3.2 11B Vision Instruct · 7 GB VRAM · Q4_K_M · llama-3-2 |
| Qwen 3 | Qwen 3 32B · 21 GB VRAM · Q4_K_M · ollama run qwen3:32b |
| Gemma 3 | Gemma 3 27B Instruct · 17 GB VRAM · Q4_K_M · ollama run gemma3:27b |
| Phi-4 Family | Phi-4 (14B) · 9 GB VRAM · Q4_K_M · ollama run phi4 |
| Phi-4 Mini | Phi-4 Mini (3.8B) · 3 GB VRAM · Q4_K_M · ollama run phi4-mini |
| Mistral Family | Mistral Small 3 (24B) · 15 GB VRAM · Q4_K_M · ollama run mistral-small |
| DeepSeek R1 | DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
Install Ollama then run the recommended model for this GPU:
ollama run qwen3:14b
Yes — the Apple M3 Pro has 36 GB unified memory and runs The 3nm upgrade to M2 Pro. Up to 36 GB unified memory at 153 GB/s. 55 t/s on 8B models. Handles Qwen 3 14B and Phi-4 14B
The Apple M3 Pro is estimated to run Llama 3.1 8B at 9.7–20 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 27 GB usable. These are modelled estimates, not measurements — see /en/methodology.
With 36 GB you can run: Llama 3.1 Family, Llama 3.2 Family, Qwen 3, Gemma 3, Phi-4 Family. Use Ollama for the easiest setup: ollama run qwen3:14b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?