readygpu

Mac mini M4 Pro 48GB vs NVIDIA GeForce RTX 4080 Super

For running models locally, priced in Germany. At 8k context the first runs 58 models fully in memory, the second 41.

In short

The Mac mini M4 Pro 48GB has more memory for models: 48 GB against 16 GB. At 8k context the Mac mini M4 Pro 48GB runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 41; only the Mac mini M4 Pro 48GB holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 2.6× as fast as the Mac mini M4 Pro 48GB (estimated, median across models). In Germany the Mac mini M4 Pro 48GB costs 2.649 € at eBay (used) and the NVIDIA GeForce RTX 4080 Super 1.990 € at Amazon: the NVIDIA GeForce RTX 4080 Super is 659 € cheaper.

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

Mac mini M4 Pro 48GB

2.566 €

eBay

Add to build
NVIDIA GeForce RTX 4080 Super

1.990 €

Amazon

Add to build

Specifications

SpecMac mini M4 Pro 48GBNVIDIA GeForce RTX 4080 Super
ChipApple M4 Pro (20-core GPU)–
Memory bus256-bit256-bit
Memory bandwidth273 GB/s736 GB/s
FP16 compute8.08 TFLOPS104 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 4080 Super
Memory–16 GB GDDR6X
Board power–320 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 4080 Super
Qwen 3.8 27B6tok/sQ8_0offload
Qwen 3.6 27B6tok/sQ8_0offload
Gemma 4 31B5tok/sQ8_0offload
Qwen 3.6 35B-A3B32tok/sQ8_0offload
Qwen 3.5 27B6tok/sQ8_0offload
Gemma 4 26B-A4B23tok/sQ8_0offload
Qwen 3.5 35B-A3B32tok/sQ8_0offload
GLM 4.7 Flash19tok/sQ8_0offload
Devstral Small 2 24B7tok/sQ8_029tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3B31tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B47tok/sQ5_K_Moffload
gpt-oss 20B40tok/sMXFP4104tok/sMXFP4
Qwen3 Coder 30B-A3B27tok/sQ8_0offload
Qwen3 32B5tok/sQ8_0offload
Gemma 4 12B14tok/sQ8_035tok/sQ8_0
Qwen 3.5 9B18tok/sQ8_046tok/sQ8_0
Mistral Small 3.2 24B7tok/sQ8_029tok/sQ4_K_M
Gemma 3 27B6tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B5tok/sQ8_0offload
Ministral 3 14B11tok/sQ8_029tok/sQ8_0
Qwen3 14B10tok/sQ8_034tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B18tok/sQ8_046tok/sQ8_0
Qwen3 8B18tok/sQ8_046tok/sQ8_0
Phi-4 14B10tok/sQ8_033tok/sQ6_K
Qwen 3.5 4B37tok/sQ8_095tok/sQ8_0
Ministral 3 8B17tok/sQ8_045tok/sQ8_0
Granite 4.2 8B17tok/sQ8_043tok/sQ8_0
Gemma 4 E4B21tok/sQ8_054tok/sQ8_0
LFM2.5 8B-A1B73tok/sQ8_0187tok/sQ8_0
Llama 3.1 8B23tok/sQ6_K60tok/sQ6_K
Qwen2.5 0.5B281tok/sQ8_0722tok/sQ8_0
Qwen3.5 0.8B191tok/sQ8_0490tok/sQ8_0
Qwen3.5 2B114tok/sQ5_K_M294tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B83tok/sQ8_0214tok/sQ8_0
MiniCPM5 2B59tok/sQ8_0151tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_0135tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_0135tok/sQ8_0
Spark X2.5 4B52tok/smlx-4bit134tok/smlx-4bit
granite vision 4.1 4b41tok/sQ8_0106tok/sQ8_0
granite 4.2 3b39tok/sQ8_0100tok/sQ8_0
LFM2.5 24B A2B38tok/sQ8_0offload
Mellum2.1 12B A2.5B Thinking38tok/sQ8_097tok/sQ8_0
FrogNano 4B 260936tok/sQ8_092tok/sQ8_0
Kimi VL A3B Thinking 250632tok/sQ8_0126tok/sQ4_K_M
Kimi VL A3B30tok/smlx-8bit98tok/smlx-6bit
DeepSeek R1 Distill Qwen 7B21tok/sQ8_053tok/sQ8_0
GLM 4 9B 041421tok/smlx-5bit53tok/smlx-5bit
DeepSeek R1 Distill Llama 8B19tok/sQ8_048tok/sQ8_0
Ministral 3 8B Reasoning 251217tok/sQ8_045tok/sQ8_0
GLM 4.6V Flash17tok/sQ8_044tok/sQ8_0
GLM 4.1V 9B Thinking15tok/smlx-8bit38tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B10tok/sQ8_033tok/sQ6_K
Qwen3.8 27B OBLITERATED8tok/smlx-4bitoffload
Devstral Small 25077tok/sQ8_029tok/sQ4_K_M
Magistral Small 25067tok/sQ8_029tok/sQ4_K_M
Magistral Small 25077tok/sQ8_029tok/sQ4_K_M
Magistral Small 25097tok/sQ8_029tok/sQ4_K_M
granite 4.2 30b5tok/sQ8_0offload
Qwen 3.5 122B-A10Bwon't runoffload
Mistral Small 4 119Bwon'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
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon'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
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon'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 Dev 72Bwon'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 mini M4 Pro 48GB or the NVIDIA GeForce RTX 4080 Super?
Choose the Mac mini M4 Pro 48GB to run bigger models. Choose the NVIDIA GeForce RTX 4080 Super for speed. Choose the NVIDIA GeForce RTX 4080 Super to spend less.
Which can run bigger models, the Mac mini M4 Pro 48GB or the NVIDIA GeForce RTX 4080 Super?
At 8k context the Mac mini M4 Pro 48GB runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 41; only the Mac mini M4 Pro 48GB holds Qwen 3.8 27B.
Which is faster for local AI, the Mac mini M4 Pro 48GB or the NVIDIA GeForce RTX 4080 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super is about 2.6× 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 4080 Super?
In Germany the Mac mini M4 Pro 48GB costs 2.649 € at eBay (used) and the NVIDIA GeForce RTX 4080 Super 1.990 € at Amazon: the NVIDIA GeForce RTX 4080 Super is 659 € cheaper.

More comparisons