readygpu

Mac mini M4 32GB vs NVIDIA GeForce RTX 4070 Super

For running models locally, priced in Germany. At 32k context the first runs 50 models fully in memory, the second 27.

In short

The Mac mini M4 32GB has more memory for models: 32 GB against 12 GB. At 32k context the Mac mini M4 32GB runs 50 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 27; only the Mac mini M4 32GB holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Super is about 4.0× as fast as the Mac mini M4 32GB (estimated, median across models). In Germany the Mac mini M4 32GB costs 1.499 € at eBay (used) and the NVIDIA GeForce RTX 4070 Super 1.800 € at eBay: the Mac mini M4 32GB is 301 € cheaper.

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

Mac mini M4 32GB

1.499 €

eBay, used (asking)

Add to build
NVIDIA GeForce RTX 4070 Super

1.800 €

eBay

Add to build

Specifications

SpecMac mini M4 32GBNVIDIA GeForce RTX 4070 Super
ChipApple M4 (10-core GPU)–
Memory bus128-bit192-bit
Memory bandwidth120 GB/s504 GB/s
FP16 compute3.76 TFLOPS71 TFLOPS
SoftwareMetalCUDA
Unified memory32 GB–
GPU can use by default21.3 GB–
GPU can use, tuned24 GB–
Operating systemmacos–
ProcessorM4 10-core–
Storage512 GB–
GPU–GeForce RTX 4070 Super
Memory–12 GB GDDR6X
Board power–220 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 32GBNVIDIA GeForce RTX 4070 Super
Qwen 3.8 27B4tok/sQ4_K_Moffload
Qwen 3.6 27B4tok/sQ5_K_Moffload
Gemma 4 31B4tok/sQ4_K_Moffload
Qwen 3.5 27B4tok/sQ5_K_Moffload
Gemma 4 26B-A4B12tok/sQ5_K_Moffload
GLM 4.7 Flash10tok/sQ4_K_Moffload
Devstral Small 2 24B4tok/sQ4_K_Moffload
gpt-oss 20B15tok/sMXFP4offload
Qwen3 Coder 30B-A3B9tok/sQ4_K_Moffload
Gemma 4 12B6tok/sQ8_029tok/sQ6_K
Qwen 3.5 9B7tok/sQ8_029tok/sQ8_0
Gemma 3 27B4tok/sQ4_K_Moffload
Mistral Small 3.2 24B4tok/sQ4_K_Moffload
Ministral 3 14B4tok/sQ8_0offload
Qwen3 14B4tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B6tok/sQ8_029tok/sQ5_K_M
Qwen3 8B6tok/sQ8_029tok/sQ5_K_M
Phi-4 14B4tok/sQ6_Koffload
Qwen 3.5 4B14tok/sQ8_056tok/sQ8_0
Ministral 3 8B6tok/sQ8_029tok/sQ5_K_M
Granite 4.2 8B5tok/sQ8_029tok/sQ4_K_M
Gemma 4 E4B9tok/sQ8_034tok/sQ8_0
LFM2.5 8B-A1B18tok/sQ8_070tok/sQ8_0
Llama 3.1 8B7tok/sQ6_K29tok/sQ6_K
Qwen2.5 0.5B84tok/sQ8_0335tok/sQ8_0
Qwen3.5 0.8B63tok/sQ8_0253tok/sQ8_0
Qwen3.5 2B42tok/sQ5_K_M168tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B28tok/sQ8_0110tok/sQ8_0
MiniCPM5 2B19tok/sQ8_076tok/sQ8_0
Spark X2.5 4B18tok/smlx-4bit73tok/smlx-4bit
LFM2.5 2.6B16tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B16tok/sQ8_064tok/sQ8_0
Mellum2.1 12B A2.5B Thinking15tok/sQ8_073tok/sQ5_K_M
FrogNano 4B 260914tok/sQ8_054tok/sQ8_0
granite vision 4.1 4b12tok/sQ8_050tok/sQ8_0
granite 4.2 3b12tok/sQ8_048tok/sQ8_0
Kimi VL A3B Thinking 250611tok/sQ8_0offload
LFM2.5 24B A2B11tok/sQ5_K_Moffload
Kimi VL A3B11tok/smlx-8bitoffload
GLM 4 9B 04148tok/smlx-5bit33tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B8tok/sQ8_031tok/sQ8_0
GLM 4.6V Flash7tok/sQ8_042tok/sQ4_K_M
DeepSeek R1 Distill Llama 8B6tok/sQ8_029tok/sQ6_K
GLM 4.1V 9B Thinking6tok/smlx-8bitoffload
Ministral 3 8B Reasoning 25126tok/sQ8_029tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14B4tok/sQ6_Koffload
Devstral Small 25074tok/sQ4_K_Moffload
Magistral Small 25064tok/sQ4_K_Moffload
Magistral Small 25074tok/sQ4_K_Moffload
Magistral Small 25094tok/sQ4_K_Moffload
Qwen 3.6 35B-A3Bwon't runoffload
Qwen 3.5 35B-A3Bwon't runoffload
Nemotron 3.5 Lightning 30B-A3Bwon't runoffload
Kimi Linear 48B-A3Bwon't runoffload
Qwen3 32Bwon't runoffload
DeepSeek R1 Distill Qwen 32Bwon't runoffload
Qwen3.8 27B OBLITERATEDwon't runoffload
granite 4.2 30bwon'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
Qwen 3.5 122B-A10Bwon'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
Mistral Small 4 119Bwon'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 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 32GB or the NVIDIA GeForce RTX 4070 Super?
Choose the Mac mini M4 32GB to run bigger models. Choose the NVIDIA GeForce RTX 4070 Super for speed. Choose the Mac mini M4 32GB to spend less.
Which can run bigger models, the Mac mini M4 32GB or the NVIDIA GeForce RTX 4070 Super?
At 32k context the Mac mini M4 32GB runs 50 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 27; only the Mac mini M4 32GB holds Qwen 3.8 27B.
Which is faster for local AI, the Mac mini M4 32GB or the NVIDIA GeForce RTX 4070 Super?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Super is about 4.0× as fast as the Mac mini M4 32GB (estimated, median across models).
What is the price difference between the Mac mini M4 32GB and the NVIDIA GeForce RTX 4070 Super?
In Germany the Mac mini M4 32GB costs 1.499 € at eBay (used) and the NVIDIA GeForce RTX 4070 Super 1.800 € at eBay: the Mac mini M4 32GB is 301 € cheaper.

More comparisons