readygpu

Mac Studio M3 Ultra 96GB vs NVIDIA RTX PRO 6000 Blackwell

For running models locally, priced in Germany. At 128k context the first runs 37 models fully in memory, the second 39.

In short

Both have 96 GB of memory for models; the Mac Studio M3 Ultra 96GB has 819 GB/s of bandwidth and the NVIDIA RTX PRO 6000 Blackwell 1,792 GB/s. At 128k context the NVIDIA RTX PRO 6000 Blackwell runs 39 of the models we track fully in memory and the Mac Studio M3 Ultra 96GB 37; only the NVIDIA RTX PRO 6000 Blackwell holds Qwen 3.8 Flash Next. 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 96GB (estimated, median across models). In Germany the Mac Studio M3 Ultra 96GB costs 5.999 € at eBay and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the Mac Studio M3 Ultra 96GB is 13.077 € cheaper.

Updated . Speeds are estimates; how they are worked out.

Mac Studio M3 Ultra 96GB

5.999 €

eBay

Add to build
NVIDIA RTX PRO 6000 Blackwell

19.076 €

eBay

Add to build

Specifications

SpecMac Studio M3 Ultra 96GBNVIDIA RTX PRO 6000 Blackwell
ChipApple M3 Ultra (80-core GPU)–
Memory bus1024-bit512-bit
Memory bandwidth819 GB/s1,792 GB/s
FP16 compute28 TFLOPS504 TFLOPS
SoftwareMetalCUDA
Unified memory96 GB–
GPU can use by default72 GB–
GPU can use, tuned88 GB–
Operating systemmacos–
ProcessorM3 Ultra 32-core–
Storage1000 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.

ModelMac Studio M3 Ultra 96GBNVIDIA RTX PRO 6000 Blackwell
Qwen 3.8 Flash Nextwon't run20tok/sUD-Q3_K_XL
Qwen 3.8 27B14tok/sQ8_029tok/sQ8_0
Qwen 3.5 122B-A10B41tok/sQ3_K_M62tok/sQ5_K_M
Qwen 3.6 27B14tok/sQ8_030tok/sQ8_0
Qwen3 Coder Next49tok/sQ6_K90tok/sQ8_0
Nemotron 3 Super 120B-A12B44tok/sUD-Q3_K_M72tok/sUD-Q4_K_M
gpt-oss 120B40tok/sMXFP484tok/sMXFP4
Gemma 4 31B12tok/sQ8_025tok/sQ8_0
Mistral Small 4 119B51tok/sUD-Q3_K_M80tok/sUD-Q5_K_M
Qwen 3.6 35B-A3B55tok/sQ8_0114tok/sQ8_0
Qwen 3.5 27B14tok/sQ8_030tok/sQ8_0
Gemma 4 26B-A4B45tok/sQ8_095tok/sQ8_0
GLM 4.5 Air10tok/sQ2_K19tok/sQ4_K_M
Qwen3 Next 80B-A3B56tok/sQ6_K104tok/sQ8_0
Qwen 3.5 35B-A3B55tok/sQ8_0114tok/sQ8_0
GLM 4.7 Flash26tok/sQ8_054tok/sQ8_0
Devstral Small 2 24B11tok/sQ8_024tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B76tok/sUD-Q6_K_XL160tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B75tok/sQ8_0155tok/sQ8_0
gpt-oss 20B57tok/sMXFP4118tok/sMXFP4
Qwen3 Coder 30B-A3B20tok/sQ8_042tok/sQ8_0
Qwen3 32B8tok/sQ8_016tok/sQ8_0
Gemma 4 12B35tok/sQ8_073tok/sQ8_0
Qwen 3.5 9B38tok/sQ8_080tok/sQ8_0
Gemma 3 27B13tok/sQ8_028tok/sQ8_0
Mistral Small 3.2 24B11tok/sQ8_024tok/sQ8_0
DeepSeek R1 Distill Qwen 32B8tok/sQ8_016tok/sQ8_0
Llama 3.3 70Bwon't run12tok/sQ5_K_M
Ministral 3 14B15tok/sQ8_031tok/sQ8_0
Qwen3 14B14tok/sQ8_030tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B19tok/sQ8_040tok/sQ8_0
Qwen3 8B19tok/sQ8_040tok/sQ8_0
Phi-4 14B13tok/sQ8_026tok/sQ8_0
Qwen 3.5 4B60tok/sQ8_0126tok/sQ8_0
Ministral 3 8B20tok/sQ8_041tok/sQ8_0
Granite 4.2 8B17tok/sQ8_036tok/sQ8_0
Gemma 4 E4B44tok/sQ8_093tok/sQ8_0
LFM2.5 8B-A1B43tok/sQ8_089tok/sQ8_0
Llama 3.1 8B22tok/sQ6_K47tok/sQ6_K
DeepSeek V4 Flashwon't runoffload
GLM 5.3 Flashwon't runoffload
MiniMax M2.7won't runoffload

Questions

Which is better for local AI, the Mac Studio M3 Ultra 96GB or the NVIDIA RTX PRO 6000 Blackwell?
Choose the NVIDIA RTX PRO 6000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the Mac Studio M3 Ultra 96GB to spend less.
Which can run bigger models, the Mac Studio M3 Ultra 96GB or the NVIDIA RTX PRO 6000 Blackwell?
At 128k context the NVIDIA RTX PRO 6000 Blackwell runs 39 of the models we track fully in memory and the Mac Studio M3 Ultra 96GB 37; only the NVIDIA RTX PRO 6000 Blackwell holds Qwen 3.8 Flash Next.
Which is faster for local AI, the Mac Studio M3 Ultra 96GB 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 96GB (estimated, median across models).
What is the price difference between the Mac Studio M3 Ultra 96GB and the NVIDIA RTX PRO 6000 Blackwell?
In Germany the Mac Studio M3 Ultra 96GB costs 5.999 € at eBay and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the Mac Studio M3 Ultra 96GB is 13.077 € cheaper.

More comparisons