readygpu

Mac Studio M4 Max 64GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in the UK. At 8k context the first runs 60 models fully in memory, the second 51.

In short

The Mac Studio M4 Max 64GB has more memory for models: 64 GB against 24 GB. At 8k context the Mac Studio M4 Max 64GB runs 60 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 51; only the Mac Studio M4 Max 64GB holds Qwen 3.5 122B-A10B. 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 64GB (estimated, median across models). In the UK the Mac Studio M4 Max 64GB costs £3,399 at eBay and the NVIDIA GeForce RTX 4090 £4,541 at Amazon: the Mac Studio M4 Max 64GB is £1,142 cheaper.

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

Mac Studio M4 Max 64GB

£3,399

eBay

Add to build
NVIDIA GeForce RTX 4090

£4,541

Amazon

Add to build

Specifications

SpecMac Studio M4 Max 64GBNVIDIA 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 memory64 GB–
GPU can use by default48 GB–
GPU can use, tuned56 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 64GBNVIDIA GeForce RTX 4090
Qwen 3.8 27B12tok/sQ8_028tok/sUD-Q6_K
Qwen 3.5 122B-A10B58tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B12tok/sQ8_027tok/sQ6_K
Qwen3 Coder Next81tok/sQ4_K_Moffload
Gemma 4 31B10tok/sQ8_027tok/sQ5_K_M
Mistral Small 4 119B83tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B64tok/sQ8_0179tok/sQ4_K_M
Qwen 3.5 27B12tok/sQ8_027tok/sQ6_K
Gemma 4 26B-A4B47tok/sQ8_095tok/sUD-Q6_K
GLM 4.5 Air25tok/sQ2_Koffload
Qwen3 Next 80B-A3B103tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B64tok/sQ8_0181tok/sQ4_K_M
GLM 4.7 Flash37tok/sQ8_094tok/sQ5_K_M
Devstral Small 2 24B13tok/sQ8_030tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B62tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B83tok/sQ6_Koffload
gpt-oss 20B81tok/sMXFP4142tok/sMXFP4
Qwen3 Coder 30B-A3B53tok/sQ8_0128tok/sQ5_K_M
Qwen3 32B10tok/sQ8_029tok/sQ4_K_M
Gemma 4 12B27tok/sQ8_048tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_064tok/sQ8_0
Mistral Small 3.2 24B13tok/sQ8_030tok/sQ6_K
Gemma 3 27B12tok/sQ8_027tok/sQ6_K
DeepSeek R1 Distill Qwen 32B10tok/sQ8_028tok/sQ4_K_M
Llama 3.3 70B8tok/sQ4_K_Moffload
Ministral 3 14B23tok/sQ8_040tok/sQ8_0
Qwen3 14B21tok/sQ8_037tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_063tok/sQ8_0
Qwen3 8B36tok/sQ8_063tok/sQ8_0
Phi-4 14B21tok/sQ8_036tok/sQ8_0
Qwen 3.5 4B74tok/sQ8_0130tok/sQ8_0
Ministral 3 8B35tok/sQ8_062tok/sQ8_0
Granite 4.2 8B33tok/sQ8_059tok/sQ8_0
Gemma 4 E4B42tok/sQ8_074tok/sQ8_0
LFM2.5 8B-A1B145tok/sQ8_0256tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K82tok/sQ6_K
Qwen2.5 0.5B562tok/sQ8_0989tok/sQ8_0
Qwen3.5 0.8B381tok/sQ8_0671tok/sQ8_0
Qwen3.5 2B228tok/sQ5_K_M402tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B167tok/sQ8_0294tok/sQ8_0
MiniCPM5 2B117tok/sQ8_0206tok/sQ8_0
LFM2.5 2.6B105tok/sQ8_0185tok/sQ8_0
LFM2.5 VL 3B105tok/sQ8_0185tok/sQ8_0
granite vision 4.1 4b83tok/sQ8_0146tok/sQ8_0
granite 4.2 3b78tok/sQ8_0137tok/sQ8_0
LFM2.5 24B A2B76tok/sQ8_0154tok/sQ6_K
Mellum2.1 12B A2.5B Thinking76tok/sQ8_0133tok/sQ8_0
Kimi VL A3B61tok/smlx-8bit107tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B41tok/sQ8_073tok/sQ8_0
DeepSeek R1 Distill Llama 8B37tok/sQ8_065tok/sQ8_0
Ministral 3 8B Reasoning 251235tok/sQ8_062tok/sQ8_0
GLM 4.6V Flash34tok/sQ8_061tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bit52tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B21tok/sQ8_036tok/sQ8_0
Devstral Small 250713tok/sQ8_035tok/sQ5_K_M
Magistral Small 250613tok/sQ8_030tok/sQ6_K
Magistral Small 250713tok/sQ8_035tok/sQ5_K_M
Magistral Small 250913tok/sQ8_035tok/sQ5_K_M
granite 4.2 30b11tok/sQ8_027tok/sQ5_K_M
DeepSeek R1 Distill Llama 70B8tok/sQ4_K_Moffload
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
gpt-oss 120Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won'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 4.6Vwon'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 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

Questions

Which is better for local AI, the Mac Studio M4 Max 64GB or the NVIDIA GeForce RTX 4090?
Choose the Mac Studio M4 Max 64GB to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the Mac Studio M4 Max 64GB to spend less.
Which can run bigger models, the Mac Studio M4 Max 64GB or the NVIDIA GeForce RTX 4090?
At 8k context the Mac Studio M4 Max 64GB runs 60 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 51; only the Mac Studio M4 Max 64GB holds Qwen 3.5 122B-A10B.
Which is faster for local AI, the Mac Studio M4 Max 64GB 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 64GB (estimated, median across models).
What is the price difference between the Mac Studio M4 Max 64GB and the NVIDIA GeForce RTX 4090?
In the UK the Mac Studio M4 Max 64GB costs £3,399 at eBay and the NVIDIA GeForce RTX 4090 £4,541 at Amazon: the Mac Studio M4 Max 64GB is £1,142 cheaper.

More comparisons