readygpu

Mac Studio M4 Max 128GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in Germany. At 64k context the first runs 74 models fully in memory, the second 45.

In short

The Mac Studio M4 Max 128GB has more memory for models: 128 GB against 24 GB. At 64k context the Mac Studio M4 Max 128GB runs 74 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 45; 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 4090 is about 1.8× as fast as the Mac Studio M4 Max 128GB (estimated, median across models). In Germany the Mac Studio M4 Max 128GB costs 9.000 € at eBay and the NVIDIA GeForce RTX 4090 3.915 € at eBay: the NVIDIA GeForce RTX 4090 is 5.085 € cheaper.

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

Mac Studio M4 Max 128GB

9.000 €

eBay

Add to build
NVIDIA GeForce RTX 4090

3.915 €

eBay

Add to build

Specifications

SpecMac Studio M4 Max 128GBNVIDIA GeForce RTX 4090
ChipApple M4 Max (40-core GPU)–
Memory bus512-bit384-bit
Memory bandwidth546 GB/s1,008 GB/s
FP16 compute16.16 TFLOPS165 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 4090
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 128GBNVIDIA GeForce RTX 4090
Qwen 3.8 Flash Next7tok/sUD-Q3_K_XLwon't run
Qwen 3.8 27B11tok/sQ8_029tok/sQ4_K_M
MiniMax M2.711tok/sUD-Q2_K_XLwon't run
Qwen 3.5 122B-A10B24tok/sQ5_K_Moffload
Qwen 3.6 27B11tok/sQ8_026tok/sQ5_K_M
gpt-oss 120B38tok/sMXFP4won't run
Qwen3 Coder Next37tok/sQ8_0offload
Nemotron 3 Super 120B-A12B21tok/sQ5_K_Mwon't run
Gemma 4 31B9tok/sQ8_0offload
Mistral Small 4 119B29tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B48tok/sQ8_0115tok/sQ4_K_M
Qwen 3.5 27B11tok/sQ8_030tok/sQ4_K_M
Gemma 4 26B-A4B37tok/sQ8_078tok/sUD-Q5_K_M
GLM 4.5 Air9tok/sQ5_K_Mwon't run
Qwen 3.5 35B-A3B48tok/sQ8_0116tok/sQ4_K_M
Qwen3 Next 80B-A3B44tok/sQ8_0offload
GLM 4.7 Flash24tok/sQ8_057tok/sQ4_K_M
Devstral Small 2 24B10tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B56tok/sUD-Q6_K_XL141tok/sMXFP4
Kimi Linear 48B-A3B57tok/sQ8_0offload
gpt-oss 20B53tok/sMXFP493tok/sMXFP4
Qwen3 Coder 30B-A3B22tok/sQ8_0offload
Qwen3 32B7tok/sQ8_0offload
Gemma 4 12B25tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B30tok/sQ8_053tok/sQ8_0
Gemma 3 27B10tok/sQ8_028tok/sQ4_K_M
Mistral Small 3.2 24B10tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B7tok/sQ8_0offload
Llama 3.3 70B4tok/sQ8_0won't run
Ministral 3 14B14tok/sQ8_029tok/sQ6_K
Qwen3 14B13tok/sQ8_027tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B19tok/sQ8_034tok/sQ8_0
Qwen3 8B19tok/sQ8_034tok/sQ8_0
Phi-4 14B12tok/sQ8_026tok/sQ5_K_M
Qwen 3.5 4B53tok/sQ8_094tok/sQ8_0
Ministral 3 8B20tok/sQ8_034tok/sQ8_0
Granite 4.2 8B18tok/sQ8_031tok/sQ8_0
Gemma 4 E4B35tok/sQ8_062tok/sQ8_0
LFM2.5 8B-A1B50tok/sQ8_088tok/sQ8_0
Llama 3.1 8B23tok/sQ6_K41tok/sQ6_K
Qwen2.5 0.5B266tok/sQ8_0468tok/sQ8_0
Qwen3.5 0.8B217tok/sQ8_0382tok/sQ8_0
Qwen3.5 2B157tok/sQ5_K_M277tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B94tok/sQ8_0166tok/sQ8_0
MiniCPM5 2B65tok/sQ8_0114tok/sQ8_0
Spark X2.5 4B64tok/smlx-4bit113tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking58tok/sQ8_0103tok/sQ8_0
FrogNano 4B 260952tok/sQ8_092tok/sQ8_0
LFM2.5 2.6B51tok/sQ8_091tok/sQ8_0
LFM2.5 VL 3B51tok/sQ8_091tok/sQ8_0
Kimi VL A3B Thinking 250641tok/sQ8_073tok/sQ8_0
Kimi VL A3B40tok/smlx-8bit71tok/smlx-8bit
granite vision 4.1 4b40tok/sQ8_070tok/sQ8_0
granite 4.2 3b38tok/sQ8_068tok/sQ8_0
GLM 4 9B 041433tok/smlx-5bit57tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B30tok/sQ8_053tok/sQ8_0
LFM2.5 24B A2B28tok/sQ8_054tok/sQ5_K_M
GLM 4.6V Flash28tok/sQ8_049tok/sQ8_0
GLM 4.1V 9B Thinking25tok/smlx-8bit43tok/smlx-8bit
DeepSeek R1 Distill Llama 8B21tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251220tok/sQ8_034tok/sQ8_0
Qwen3.8 27B OBLITERATED14tok/smlx-4bitoffload
DeepSeek R1 Distill Qwen 14B12tok/sQ8_027tok/sQ5_K_M
GLM 4.5V10tok/sQ4_K_Mwon't run
Devstral Small 250710tok/sQ8_0offload
Magistral Small 250610tok/sQ8_0offload
Magistral Small 250710tok/sQ8_0offload
Magistral Small 250910tok/sQ8_0offload
GLM 4.6V10tok/sQ4_K_Mwon't run
granite 4.2 30b7tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B4tok/sQ8_0won't run
Devstral 2 123B Instruct 25124tok/sQ4_K_Mwon't run
Kimi Dev 72B4tok/sQ8_0won't run
Mistral Medium 3.5 128B4tok/sQ4_K_Mwon't run
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won'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
GLM 4.5won't runwon't run
GLM 4.6won't runwon't run
GLM 4.7won't runwon't run
GLM 5won'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 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

Questions

Which is better for local AI, the Mac Studio M4 Max 128GB or the NVIDIA GeForce RTX 4090?
Choose the Mac Studio M4 Max 128GB to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 4090 to spend less.
Which can run bigger models, the Mac Studio M4 Max 128GB or the NVIDIA GeForce RTX 4090?
At 64k context the Mac Studio M4 Max 128GB runs 74 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 45; 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 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 1.8× 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 4090?
In Germany the Mac Studio M4 Max 128GB costs 9.000 € at eBay and the NVIDIA GeForce RTX 4090 3.915 € at eBay: the NVIDIA GeForce RTX 4090 is 5.085 € cheaper.

More comparisons