readygpu

Mac mini M4 Pro 64GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in the US. At 64k context the first runs 34 models fully in memory, the second 22.

In short

The Mac mini M4 Pro 64GB has more memory for models: 64 GB against 24 GB. At 64k context the Mac mini M4 Pro 64GB runs 34 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 22; only the Mac mini M4 Pro 64GB holds Qwen 3.5 122B-A10B. On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.8× as fast as the Mac mini M4 Pro 64GB (estimated, median across models). In the US the Mac mini M4 Pro 64GB costs $2,900 at eBay and the NVIDIA GeForce RTX 4090 $2,073 at eBay: the NVIDIA GeForce RTX 4090 is $826 cheaper.

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

Mac mini M4 Pro 64GB

$2,900

eBay

Add to build
NVIDIA GeForce RTX 4090

$2,073

eBay

Add to build

Specifications

SpecMac mini M4 Pro 64GBNVIDIA GeForce RTX 4090
ChipApple M4 Pro (20-core GPU)–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s1,008 GB/s
FP16 compute8.08 TFLOPS165 TFLOPS
SoftwareMetalCUDA
Unified memory64 GB–
GPU can use by default48 GB–
GPU can use, tuned56 GB–
Operating systemmacos–
ProcessorM4 Pro 14-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 mini M4 Pro 64GBNVIDIA GeForce RTX 4090
Qwen 3.8 27B5tok/sQ8_030tok/sUD-Q4_K_M
Qwen 3.5 122B-A10B21tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B5tok/sQ8_026tok/sQ5_K_M
Qwen3 Coder Next26tok/sQ4_K_Moffload
Gemma 4 31B5tok/sQ8_0offload
Mistral Small 4 119B27tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B24tok/sQ8_0115tok/sUD-Q4_K_M
Qwen 3.5 27B5tok/sQ8_030tok/sQ4_K_M
Gemma 4 26B-A4B19tok/sQ8_078tok/sUD-Q5_K_M
Qwen3 Next 80B-A3B31tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B24tok/sQ8_0116tok/sQ4_K_M
GLM 4.7 Flash12tok/sQ8_057tok/sQ4_K_M
Devstral Small 2 24B5tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B28tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B35tok/sQ6_Koffload
gpt-oss 20B26tok/sMXFP493tok/sMXFP4
Qwen3 Coder 30B-A3B11tok/sQ8_0offload
Qwen3 32B4tok/sQ6_Koffload
Gemma 4 12B13tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B15tok/sQ8_053tok/sQ8_0
Gemma 3 27B5tok/sQ8_028tok/sQ4_K_M
Mistral Small 3.2 24B5tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B4tok/sQ6_Koffload
Ministral 3 14B7tok/sQ8_029tok/sQ6_K
Qwen3 14B7tok/sQ8_027tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B10tok/sQ8_034tok/sQ8_0
Qwen3 8B10tok/sQ8_034tok/sQ8_0
Phi-4 14B6tok/sQ8_026tok/sQ5_K_M
Qwen 3.5 4B27tok/sQ8_094tok/sQ8_0
Ministral 3 8B10tok/sQ8_034tok/sQ8_0
Granite 4.2 8B9tok/sQ8_031tok/sQ8_0
Gemma 4 E4B18tok/sQ8_062tok/sQ8_0
LFM2.5 8B-A1B25tok/sQ8_088tok/sQ8_0
Llama 3.1 8B12tok/sQ6_K41tok/sQ6_K
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
GLM 4.5 Airwon't runwon't run
Llama 3.3 70Bwon't runwon't run

Questions

Which is better for local AI, the Mac mini M4 Pro 64GB or the NVIDIA GeForce RTX 4090?
Choose the Mac mini M4 Pro 64GB 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 mini M4 Pro 64GB or the NVIDIA GeForce RTX 4090?
At 64k context the Mac mini M4 Pro 64GB runs 34 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 22; only the Mac mini M4 Pro 64GB holds Qwen 3.5 122B-A10B.
Which is faster for local AI, the Mac mini M4 Pro 64GB or the NVIDIA GeForce RTX 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.8× as fast as the Mac mini M4 Pro 64GB (estimated, median across models).
What is the price difference between the Mac mini M4 Pro 64GB and the NVIDIA GeForce RTX 4090?
In the US the Mac mini M4 Pro 64GB costs $2,900 at eBay and the NVIDIA GeForce RTX 4090 $2,073 at eBay: the NVIDIA GeForce RTX 4090 is $826 cheaper.

More comparisons