readygpu

Mac Studio M4 Max 128GB vs NVIDIA GeForce RTX 5090

For running models locally, priced in the US. At 128k context the first runs 39 models fully in memory, the second 24.

In short

The Mac Studio M4 Max 128GB has more memory for models: 128 GB against 32 GB. At 128k context the Mac Studio M4 Max 128GB runs 39 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 24; only the Mac Studio M4 Max 128GB holds Qwen 3.8 Flash Next. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 3.3× as fast as the Mac Studio M4 Max 128GB (estimated, median across models). In the US the Mac Studio M4 Max 128GB costs $4,999 at eBay and the NVIDIA GeForce RTX 5090 $4,921 at eBay: the NVIDIA GeForce RTX 5090 is $78 cheaper.

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

Mac Studio M4 Max 128GB

$4,999

eBay

Add to build
NVIDIA GeForce RTX 5090

$4,921

eBay

Add to build

Specifications

SpecMac Studio M4 Max 128GBNVIDIA GeForce RTX 5090
ChipApple M4 Max (40-core GPU)–
Memory bus512-bit512-bit
Memory bandwidth546 GB/s1,792 GB/s
FP16 compute16.16 TFLOPS209 TFLOPS
SoftwareMetalCUDA
Unified memory128 GB–
GPU can use by default96 GB–
GPU can use, tuned120 GB–
Operating systemmacos–
ProcessorM4 Max 16-core–
Storage1000 GB–
GPU–GeForce RTX 5090
Memory–32 GB GDDR7
Board power–575 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 M4 Max 128GBNVIDIA GeForce RTX 5090
Qwen 3.8 Flash Next6tok/sUD-Q3_K_XLwon't run
Qwen 3.8 27B9tok/sQ8_036tok/sUD-Q6_K
Qwen 3.5 122B-A10B20tok/sQ5_K_Moffload
Qwen 3.6 27B10tok/sQ8_036tok/sQ6_K
Qwen3 Coder Next29tok/sQ8_0offload
gpt-oss 120B27tok/sMXFP4won't run
Nemotron 3 Super 120B-A12B23tok/sUD-Q4_K_Moffload
Gemma 4 31B8tok/sQ8_037tok/sQ4_K_M
Mistral Small 4 119B26tok/sUD-Q5_K_Moffload
Qwen 3.6 35B-A3B37tok/sQ8_0128tok/sUD-Q6_K
Qwen 3.5 27B10tok/sQ8_036tok/sQ6_K
Gemma 4 26B-A4B30tok/sQ8_095tok/sQ8_0
GLM 4.5 Air6tok/sQ4_K_Mwon't run
Qwen 3.5 35B-A3B37tok/sQ8_0129tok/sQ6_K
Qwen3 Next 80B-A3B33tok/sQ8_0offload
GLM 4.7 Flash17tok/sQ8_060tok/sQ6_K
Devstral Small 2 24B8tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B51tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B50tok/sQ8_0227tok/sQ4_K_M
gpt-oss 20B38tok/sMXFP4118tok/sMXFP4
Qwen3 Coder 30B-A3B13tok/sQ8_045tok/sQ4_K_M
Qwen3 32B5tok/sQ8_0offload
Gemma 4 12B23tok/sQ8_073tok/sQ8_0
Qwen 3.5 9B26tok/sQ8_080tok/sQ8_0
Gemma 3 27B9tok/sQ8_037tok/sQ5_K_M
Mistral Small 3.2 24B8tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B5tok/sQ8_0offload
Llama 3.3 70B4tok/sQ5_K_Mwon't run
Ministral 3 14B10tok/sQ8_036tok/sQ5_K_M
Qwen3 14B10tok/sQ8_035tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_040tok/sQ8_0
Qwen3 8B13tok/sQ8_040tok/sQ8_0
Phi-4 14B8tok/sQ8_0offload
Qwen 3.5 4B40tok/sQ8_0126tok/sQ8_0
Ministral 3 8B13tok/sQ8_041tok/sQ8_0
Granite 4.2 8B12tok/sQ8_036tok/sQ8_0
Gemma 4 E4B30tok/sQ8_093tok/sQ8_0
LFM2.5 8B-A1B28tok/sQ8_089tok/sQ8_0
Llama 3.1 8B15tok/sQ6_K47tok/sQ6_K
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
MiniMax M2.7won't runwon't run

Questions

Which is better for local AI, the Mac Studio M4 Max 128GB or the NVIDIA GeForce RTX 5090?
Choose the Mac Studio M4 Max 128GB to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed. Choose the NVIDIA GeForce RTX 5090 to spend less.
Which can run bigger models, the Mac Studio M4 Max 128GB or the NVIDIA GeForce RTX 5090?
At 128k context the Mac Studio M4 Max 128GB runs 39 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 24; only the Mac Studio M4 Max 128GB holds Qwen 3.8 Flash Next.
Which is faster for local AI, the Mac Studio M4 Max 128GB or the NVIDIA GeForce RTX 5090?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 3.3× as fast as the Mac Studio M4 Max 128GB (estimated, median across models).
What is the price difference between the Mac Studio M4 Max 128GB and the NVIDIA GeForce RTX 5090?
In the US the Mac Studio M4 Max 128GB costs $4,999 at eBay and the NVIDIA GeForce RTX 5090 $4,921 at eBay: the NVIDIA GeForce RTX 5090 is $78 cheaper.

More comparisons