readygpu

Mac mini M4 Pro 48GB vs NVIDIA GeForce RTX 3090 Ti

For running models locally, priced in the UK. At 64k context the first runs 30 models fully in memory, the second 22.

In short

The Mac mini M4 Pro 48GB has more memory for models: 48 GB against 24 GB. At 64k context the Mac mini M4 Pro 48GB runs 30 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 22; only the Mac mini M4 Pro 48GB holds Gemma 4 31B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 3.8× as fast as the Mac mini M4 Pro 48GB (estimated, median across models). In the UK the Mac mini M4 Pro 48GB costs £3,000 at eBay and the NVIDIA GeForce RTX 3090 Ti £2,199 at Amazon: the NVIDIA GeForce RTX 3090 Ti is £801 cheaper.

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

Mac mini M4 Pro 48GB

£3,000

eBay

Add to build
NVIDIA GeForce RTX 3090 Ti

£2,199

Amazon

Add to build

Specifications

SpecMac mini M4 Pro 48GBNVIDIA GeForce RTX 3090 Ti
ChipApple M4 Pro (20-core GPU)–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s1,008 GB/s
FP16 compute8.08 TFLOPS80 TFLOPS
SoftwareMetalCUDA
Unified memory48 GB–
GPU can use by default36 GB–
GPU can use, tuned40 GB–
Operating systemmacos–
ProcessorM4 Pro 14-core–
Storage512 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 mini M4 Pro 48GBNVIDIA GeForce RTX 3090 Ti
Qwen 3.8 27B5tok/sQ8_030tok/sUD-Q4_K_M
Qwen 3.6 27B5tok/sQ8_026tok/sQ5_K_M
Gemma 4 31B6tok/sQ6_Koffload
Qwen 3.6 35B-A3B28tok/sUD-Q6_K115tok/sUD-Q4_K_M
Qwen 3.5 27B5tok/sQ8_030tok/sQ4_K_M
Gemma 4 26B-A4B19tok/sQ8_078tok/sUD-Q5_K_M
Qwen 3.5 35B-A3B28tok/sQ6_K116tok/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-A3B39tok/sQ5_K_Moffload
gpt-oss 20B26tok/sMXFP493tok/sMXFP4
Qwen3 Coder 30B-A3B12tok/sQ6_Koffload
Qwen3 32B5tok/sQ4_K_Moffload
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 32B5tok/sQ4_K_Moffload
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
Qwen 3.5 122B-A10Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
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 48GB or the NVIDIA GeForce RTX 3090 Ti?
Choose the Mac mini M4 Pro 48GB 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 mini M4 Pro 48GB or the NVIDIA GeForce RTX 3090 Ti?
At 64k context the Mac mini M4 Pro 48GB runs 30 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 22; only the Mac mini M4 Pro 48GB holds Gemma 4 31B.
Which is faster for local AI, the Mac mini M4 Pro 48GB or the NVIDIA GeForce RTX 3090 Ti?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 Ti is about 3.8× as fast as the Mac mini M4 Pro 48GB (estimated, median across models).
What is the price difference between the Mac mini M4 Pro 48GB and the NVIDIA GeForce RTX 3090 Ti?
In the UK the Mac mini M4 Pro 48GB costs £3,000 at eBay and the NVIDIA GeForce RTX 3090 Ti £2,199 at Amazon: the NVIDIA GeForce RTX 3090 Ti is £801 cheaper.

More comparisons