作者： Jakub Rusinowski · 最后更新： 2026年7月12日
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) | 24–49 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | 3.2–6.7 tok/s (estimated) |
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
All models below run comfortably in 96 GB unified memory with Q4_K_M quantization.
| Llama 3.3 | Llama 3.3 70B Instruct · 43 GB VRAM · Q4_K_M · ollama run llama3.3 |
| Llama 3.1 Family | Llama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| DeepSeek R1 | DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
| 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 |
| Mistral Small 3.1 | Mistral Small 3.1 24B · 15 GB VRAM · Q4_K_M · ollama run mistral-small3.1 |
| Phi-4 Family | Phi-4 (14B) · 9 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 is estimated to run Llama 3.1 8B at 24–49 tok/s with Q4_K_M quantization. For Llama 3.3 70B the estimate is 3.2–6.7 tok/s. These are modelled estimates, not measurements — see /en/methodology.
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?