Mac Studio M3 Ultra 512GB vs NVIDIA RTX PRO 6000 Blackwell
For running models locally, priced in Germany. At 128k context the first runs 42 models fully in memory, the second 39.
In short
The Mac Studio M3 Ultra 512GB has more memory for models: 512 GB against 96 GB. At 128k context the Mac Studio M3 Ultra 512GB runs 42 of the models we track fully in memory and the NVIDIA RTX PRO 6000 Blackwell 39; only the Mac Studio M3 Ultra 512GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 2.1× as fast as the Mac Studio M3 Ultra 512GB (estimated, median across models). In Germany the Mac Studio M3 Ultra 512GB costs 18.995 € at eBay (used) and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the Mac Studio M3 Ultra 512GB is 81 € cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Mac Studio M3 Ultra 512GB | NVIDIA RTX PRO 6000 Blackwell |
|---|---|---|
| Chip | Apple M3 Ultra (80-core GPU) | – |
| Memory bus | 1024-bit | 512-bit |
| Memory bandwidth | 819 GB/s | 1,792 GB/s |
| FP16 compute | 28 TFLOPS | 504 TFLOPS |
| Software | Metal | CUDA |
| Unified memory | 512 GB | – |
| GPU can use by default | 384 GB | – |
| GPU can use, tuned | 504 GB | – |
| Operating system | macos | – |
| Processor | M3 Ultra 32-core | – |
| Storage | 2000 GB | – |
| GPU | – | RTX PRO 6000 Blackwell |
| Memory | – | 96 GB GDDR7 |
| Board power | – | 600 W |
| PCIe generation | – | Gen 5 |
| PCIe lanes | – | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Mac Studio M3 Ultra 512GB | NVIDIA RTX PRO 6000 Blackwell |
|---|---|---|
| DeepSeek V4 Flash | 14tok/sUD-Q4_K_XL | offload |
| GLM 5.3 Flash | 11tok/sQ8_0 | offload |
| Qwen 3.8 Flash Next | 5tok/sQ8_0 | 20tok/sUD-Q3_K_XL |
| Qwen 3.8 27B | 14tok/sQ8_0 | 29tok/sQ8_0 |
| MiniMax M2.7 | 7tok/sQ8_0 | offload |
| Qwen 3.5 122B-A10B | 23tok/sQ8_0 | 62tok/sQ5_K_M |
| Qwen 3.6 27B | 14tok/sQ8_0 | 30tok/sQ8_0 |
| Qwen3 Coder Next | 43tok/sQ8_0 | 90tok/sQ8_0 |
| gpt-oss 120B | 40tok/sMXFP4 | 84tok/sMXFP4 |
| Nemotron 3 Super 120B-A12B | 23tok/sQ8_0 | 72tok/sUD-Q4_K_M |
| Gemma 4 31B | 12tok/sQ8_0 | 25tok/sQ8_0 |
| Mistral Small 4 119B | 30tok/sQ8_0 | 80tok/sUD-Q5_K_M |
| Qwen 3.6 35B-A3B | 55tok/sQ8_0 | 114tok/sQ8_0 |
| Qwen 3.5 27B | 14tok/sQ8_0 | 30tok/sQ8_0 |
| Gemma 4 26B-A4B | 45tok/sQ8_0 | 95tok/sQ8_0 |
| GLM 4.5 Air | 8tok/sQ8_0 | 19tok/sQ4_K_M |
| Qwen 3.5 35B-A3B | 55tok/sQ8_0 | 114tok/sQ8_0 |
| Qwen3 Next 80B-A3B | 50tok/sQ8_0 | 104tok/sQ8_0 |
| GLM 4.7 Flash | 26tok/sQ8_0 | 54tok/sQ8_0 |
| Devstral Small 2 24B | 11tok/sQ8_0 | 24tok/sQ8_0 |
| Nemotron 3.5 Lightning 30B-A3B | 76tok/sUD-Q6_K_XL | 160tok/sUD-Q6_K_XL |
| Kimi Linear 48B-A3B | 75tok/sQ8_0 | 155tok/sQ8_0 |
| gpt-oss 20B | 57tok/sMXFP4 | 118tok/sMXFP4 |
| Qwen3 Coder 30B-A3B | 20tok/sQ8_0 | 42tok/sQ8_0 |
| Qwen3 32B | 8tok/sQ8_0 | 16tok/sQ8_0 |
| Gemma 4 12B | 35tok/sQ8_0 | 73tok/sQ8_0 |
| Qwen 3.5 9B | 38tok/sQ8_0 | 80tok/sQ8_0 |
| Gemma 3 27B | 13tok/sQ8_0 | 28tok/sQ8_0 |
| Mistral Small 3.2 24B | 11tok/sQ8_0 | 24tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 32B | 8tok/sQ8_0 | 16tok/sQ8_0 |
| Llama 3.3 70B | 5tok/sQ8_0 | 12tok/sQ5_K_M |
| Ministral 3 14B | 15tok/sQ8_0 | 31tok/sQ8_0 |
| Qwen3 14B | 14tok/sQ8_0 | 30tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 19tok/sQ8_0 | 40tok/sQ8_0 |
| Qwen3 8B | 19tok/sQ8_0 | 40tok/sQ8_0 |
| Phi-4 14B | 13tok/sQ8_0 | 26tok/sQ8_0 |
| Qwen 3.5 4B | 60tok/sQ8_0 | 126tok/sQ8_0 |
| Ministral 3 8B | 20tok/sQ8_0 | 41tok/sQ8_0 |
| Granite 4.2 8B | 17tok/sQ8_0 | 36tok/sQ8_0 |
| Gemma 4 E4B | 44tok/sQ8_0 | 93tok/sQ8_0 |
| LFM2.5 8B-A1B | 43tok/sQ8_0 | 89tok/sQ8_0 |
| Llama 3.1 8B | 22tok/sQ6_K | 47tok/sQ6_K |
Questions
- Which is better for local AI, the Mac Studio M3 Ultra 512GB or the NVIDIA RTX PRO 6000 Blackwell?
- Choose the Mac Studio M3 Ultra 512GB to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the Mac Studio M3 Ultra 512GB to spend less.
- Which can run bigger models, the Mac Studio M3 Ultra 512GB or the NVIDIA RTX PRO 6000 Blackwell?
- At 128k context the Mac Studio M3 Ultra 512GB runs 42 of the models we track fully in memory and the NVIDIA RTX PRO 6000 Blackwell 39; only the Mac Studio M3 Ultra 512GB holds DeepSeek V4 Flash.
- Which is faster for local AI, the Mac Studio M3 Ultra 512GB or the NVIDIA RTX PRO 6000 Blackwell?
- On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 2.1× as fast as the Mac Studio M3 Ultra 512GB (estimated, median across models).
- What is the price difference between the Mac Studio M3 Ultra 512GB and the NVIDIA RTX PRO 6000 Blackwell?
- In Germany the Mac Studio M3 Ultra 512GB costs 18.995 € at eBay (used) and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the Mac Studio M3 Ultra 512GB is 81 € cheaper.
More comparisons
- Mac Studio M3 Ultra 256GB vs Mac Studio M3 Ultra 512GB
- Mac Studio M3 Ultra 256GB vs NVIDIA RTX PRO 6000 Blackwell
- Mac Studio M3 Ultra 512GB vs Mac Studio M3 Ultra 96GB
- Mac Studio M3 Ultra 96GB vs NVIDIA RTX PRO 6000 Blackwell
- NVIDIA GeForce RTX 3090 Ti vs NVIDIA RTX PRO 6000 Blackwell
- NVIDIA GeForce RTX 5090 vs NVIDIA RTX PRO 6000 Blackwell