readygpu

Mac Studio M4 Max 64GB vs NVIDIA GeForce RTX 3090 Ti

For running models locally, priced in Germany. At 128k context the first runs 56 models fully in memory, the second 28.

In short

The Mac Studio M4 Max 64GB has more memory for models: 64 GB against 24 GB. At 128k context the Mac Studio M4 Max 64GB runs 56 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 28; only the Mac Studio M4 Max 64GB holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 1.8× as fast as the Mac Studio M4 Max 64GB (estimated, median across models). In Germany the Mac Studio M4 Max 64GB costs 4.000 € at eBay and the NVIDIA GeForce RTX 3090 Ti 2.790 € at Amazon: the NVIDIA GeForce RTX 3090 Ti is 1.210 € cheaper.

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

Mac Studio M4 Max 64GB

4.000 €

eBay

Add to build
NVIDIA GeForce RTX 3090 Ti

2.790 €

Amazon

Add to build

Specifications

SpecMac Studio M4 Max 64GBNVIDIA GeForce RTX 3090 Ti
ChipApple M4 Max (40-core GPU)–
Memory bus512-bit384-bit
Memory bandwidth546 GB/s1,008 GB/s
FP16 compute16.16 TFLOPS80 TFLOPS
SoftwareMetalCUDA
Unified memory64 GB–
GPU can use by default48 GB–
GPU can use, tuned56 GB–
Operating systemmacos–
ProcessorM4 Max 16-core–
Storage1000 GB–
GPU–GeForce RTX 3090 Ti
Memory–24 GB GDDR6X
Board power–450 W
PCIe generation–Gen 4
PCIe lanes–x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelMac Studio M4 Max 64GBNVIDIA GeForce RTX 3090 Ti
Qwen 3.8 27B9tok/sQ8_0offload
Qwen 3.5 122B-A10B32tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B10tok/sQ8_0offload
Gemma 4 31B8tok/sQ8_0offload
Mistral Small 4 119B40tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B37tok/sQ8_0offload
Qwen 3.5 27B10tok/sQ8_0offload
Gemma 4 26B-A4B30tok/sQ8_064tok/sQ5_K_M
Qwen 3.5 35B-A3B37tok/sQ8_0offload
GLM 4.7 Flash17tok/sQ8_0offload
Devstral Small 2 24B8tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B51tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B60tok/sQ6_Koffload
gpt-oss 20B38tok/sMXFP466tok/sMXFP4
Qwen3 Coder 30B-A3B13tok/sQ8_0offload
Gemma 4 12B23tok/sQ8_041tok/sQ8_0
Qwen 3.5 9B26tok/sQ8_045tok/sQ8_0
Gemma 3 27B9tok/sQ8_0offload
Mistral Small 3.2 24B8tok/sQ8_0offload
Ministral 3 14B10tok/sQ8_0offload
Qwen3 14B10tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_0offload
Qwen3 8B13tok/sQ8_0offload
Phi-4 14B8tok/sQ8_0offload
Qwen 3.5 4B40tok/sQ8_071tok/sQ8_0
Ministral 3 8B13tok/sQ8_027tok/sQ4_K_M
Granite 4.2 8B12tok/sQ8_0offload
Gemma 4 E4B30tok/sQ8_052tok/sQ8_0
LFM2.5 8B-A1B28tok/sQ8_050tok/sQ8_0
Llama 3.1 8B15tok/sQ6_K27tok/sQ5_K_M
Qwen2.5 0.5B166tok/sQ8_0292tok/sQ8_0
Qwen3.5 0.8B145tok/sQ8_0256tok/sQ8_0
Qwen3.5 2B116tok/sQ5_K_M204tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B63tok/sQ8_0111tok/sQ8_0
Mellum2.1 12B A2.5B Thinking47tok/sQ8_082tok/sQ8_0
Spark X2.5 4B45tok/smlx-4bit79tok/smlx-4bit
MiniCPM5 2B43tok/sQ8_075tok/sQ8_0
LFM2.5 2.6B33tok/sQ8_057tok/sQ8_0
LFM2.5 VL 3B33tok/sQ8_057tok/sQ8_0
Kimi VL A3B Thinking 250630tok/sQ8_052tok/sQ8_0
Kimi VL A3B29tok/smlx-8bit51tok/smlx-8bit
GLM 4 9B 041426tok/smlx-5bit46tok/smlx-5bit
granite vision 4.1 4b25tok/sQ8_044tok/sQ8_0
granite 4.2 3b24tok/sQ8_043tok/sQ8_0
GLM 4.6V Flash23tok/sQ8_041tok/sQ8_0
DeepSeek R1 Distill Qwen 7B23tok/sQ8_040tok/sQ8_0
GLM 4.1V 9B Thinking21tok/smlx-8bit37tok/smlx-8bit
LFM2.5 24B A2B17tok/sQ8_0offload
DeepSeek R1 Distill Llama 8B14tok/sQ8_027tok/sQ5_K_M
Ministral 3 8B Reasoning 251213tok/sQ8_027tok/sQ4_K_M
Qwen3.8 27B OBLITERATED12tok/smlx-4bitoffload
DeepSeek R1 Distill Qwen 14B9tok/sQ8_0offload
Devstral Small 25078tok/sQ8_0offload
Magistral Small 25068tok/sQ8_0offload
Magistral Small 25078tok/sQ8_0offload
Magistral Small 25098tok/sQ8_0offload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run
granite 4.2 30bwon't runwon't run

Questions

Which is better for local AI, the Mac Studio M4 Max 64GB or the NVIDIA GeForce RTX 3090 Ti?
Choose the Mac Studio M4 Max 64GB to run bigger models. Choose the NVIDIA GeForce RTX 3090 Ti for speed. Choose the NVIDIA GeForce RTX 3090 Ti to spend less.
Which can run bigger models, the Mac Studio M4 Max 64GB or the NVIDIA GeForce RTX 3090 Ti?
At 128k context the Mac Studio M4 Max 64GB runs 56 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 28; only the Mac Studio M4 Max 64GB holds Qwen 3.8 27B.
Which is faster for local AI, the Mac Studio M4 Max 64GB or the NVIDIA GeForce RTX 3090 Ti?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 1.8× as fast as the Mac Studio M4 Max 64GB (estimated, median across models).
What is the price difference between the Mac Studio M4 Max 64GB and the NVIDIA GeForce RTX 3090 Ti?
In Germany the Mac Studio M4 Max 64GB costs 4.000 € at eBay and the NVIDIA GeForce RTX 3090 Ti 2.790 € at Amazon: the NVIDIA GeForce RTX 3090 Ti is 1.210 € cheaper.

More comparisons