Up to 96 GB unified memory. 90 t/s on 8B, 24 t/s on 70B models. Popular in Mac Studio configurations. Silent, 40W system power. A strong used value at $1,500–2,000.
| VRAM | 96 GB unified memory |
| Memory Bandwidth | 400 GB/s |
| TDP | 40 W |
| Architecture | ARM, 5nm TSMC |
| Release Year | 2023 |
| MSRP at Launch | $3,499 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | ~90 tokens/sec |
| Inference Speed (Llama 3.3 70B Q4_K_M) | ~24 tokens/sec |
All models below run comfortably in 96 GB unified memory with Q4_K_M quantization.
| Llama 3.3 | 24 GB VRAM · Q2_K_XS (Tight) · ollama run llama3.3 |
| Llama 3.1 Family | 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| DeepSeek R1 | 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
| Qwen 3 | 80 GB VRAM · Q4_K_M · ollama run qwen3:235b-a22b |
| Gemma 3 | 16 GB VRAM · Q4_K_M · ollama run gemma3:27b |
| Mistral Small 3.1 | 14 GB VRAM · Q4_K_M · ollama run mistral-small3.1 |
| Phi-4 Family | 10 GB VRAM · Q4_K_M · ollama run phi4 |
Install Ollama then run the recommended model for this GPU:
ollama run llama3.3:70b
Yes — the Apple M2 Max has 96 GB unified memory and runs Up to 96 GB unified memory. 90 t/s on 8B, 24 t/s on 70B models. Popular in Mac Studio configurations. Silent, 40W system
The Apple M2 Max runs Llama 3.1 8B at ~90 tokens/sec with Q4_K_M quantization. For the 70B model it achieves ~24 tokens/sec.
With 96 GB you can run: Llama 3.3, Llama 3.1 Family, DeepSeek R1, Qwen 3, Gemma 3. Use Ollama for the easiest setup: ollama run llama3.3:70b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?