Mac mini M4 16GB vs NVIDIA GeForce RTX 4070
For running models locally, priced in Germany. At 8k context the first runs 33 models fully in memory, the second 34.
In short
The Mac mini M4 16GB has more memory for models: 16 GB against 12 GB. At 8k context the NVIDIA GeForce RTX 4070 runs 34 of the models we track fully in memory and the Mac mini M4 16GB 33; only the NVIDIA GeForce RTX 4070 holds Kimi VL A3B Thinking 2506. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 4.0× as fast as the Mac mini M4 16GB (estimated, median across models). In Germany the Mac mini M4 16GB costs 750 € at eBay and the NVIDIA GeForce RTX 4070 700 € at eBay: the NVIDIA GeForce RTX 4070 is 50 € cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Mac mini M4 16GB | NVIDIA GeForce RTX 4070 |
|---|---|---|
| Chip | Apple M4 (10-core GPU) | – |
| Memory bus | 128-bit | 192-bit |
| Memory bandwidth | 120 GB/s | 504.2 GB/s |
| FP16 compute | 3.76 TFLOPS | 29.146 TFLOPS |
| Software | Metal | CUDA |
| Unified memory | 16 GB | – |
| GPU can use by default | 10.7 GB | – |
| GPU can use, tuned | 10.666666666666666 GB | – |
| Operating system | macos | – |
| Processor | M4 10-core | – |
| Storage | 256 GB | – |
| GPU | – | GeForce RTX 4070 |
| Memory | – | 12 GB GDDR6X |
| Board power | – | 200 W |
| PCIe generation | – | Gen 4 |
| PCIe lanes | – | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Mac mini M4 16GB | NVIDIA GeForce RTX 4070 |
|---|---|---|
| Gemma 4 12B | 8tok/sQ6_K | 31tok/sQ6_K |
| Qwen 3.5 9B | 8tok/sQ8_0 | 32tok/sQ8_0 |
| Ministral 3 14B | 8tok/sQ4_K_M | 29tok/sQ5_K_M |
| Qwen3 14B | 8tok/sQ4_K_M | 30tok/sQ4_K_M |
| DeepSeek R1 0528 Qwen3 8B | 8tok/sQ8_0 | 32tok/sQ8_0 |
| Qwen3 8B | 8tok/sQ8_0 | 32tok/sQ8_0 |
| Phi-4 14B | 7tok/sQ4_K_M | 30tok/sQ4_K_M |
| Qwen 3.5 4B | 16tok/sQ8_0 | 65tok/sQ8_0 |
| Ministral 3 8B | 8tok/sQ8_0 | 31tok/sQ8_0 |
| Granite 4.2 8B | 7tok/sQ8_0 | 29tok/sQ8_0 |
| Gemma 4 E4B | 9tok/sQ8_0 | 37tok/sQ8_0 |
| LFM2.5 8B-A1B | 32tok/sQ8_0 | 128tok/sQ8_0 |
| Llama 3.1 8B | 10tok/sQ6_K | 41tok/sQ6_K |
| Qwen2.5 0.5B | 124tok/sQ8_0 | 495tok/sQ8_0 |
| Qwen3.5 0.8B | 84tok/sQ8_0 | 336tok/sQ8_0 |
| Qwen3.5 2B | 50tok/sQ5_K_M | 201tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 1.5B | 37tok/sQ8_0 | 147tok/sQ8_0 |
| MiniCPM5 2B | 26tok/sQ8_0 | 103tok/sQ8_0 |
| LFM2.5 2.6B | 23tok/sQ8_0 | 93tok/sQ8_0 |
| LFM2.5 VL 3B | 23tok/sQ8_0 | 93tok/sQ8_0 |
| Spark X2.5 4B | 23tok/smlx-4bit | 92tok/smlx-4bit |
| Mellum2.1 12B A2.5B Thinking | 21tok/sQ5_K_M | 85tok/sQ5_K_M |
| granite vision 4.1 4b | 18tok/sQ8_0 | 73tok/sQ8_0 |
| Ministral 3 3B Instruct 2512 | 17tok/sQ8_0 | 69tok/sQ8_0 |
| granite 4.2 3b | 17tok/sQ8_0 | 69tok/sQ8_0 |
| FrogNano 4B 2609 | 16tok/sQ8_0 | 63tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 7B | 9tok/sQ8_0 | 37tok/sQ8_0 |
| GLM 4 9B 0414 | 9tok/smlx-5bit | 36tok/smlx-5bit |
| DeepSeek R1 Distill Llama 8B | 8tok/sQ8_0 | 33tok/sQ8_0 |
| Ministral 3 14B Reasoning 2512 | 8tok/sQ4_K_M | 29tok/sQ5_K_M |
| Ministral 3 8B Reasoning 2512 | 8tok/sQ8_0 | 31tok/sQ8_0 |
| GLM 4.6V Flash | 8tok/sQ8_0 | 30tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 14B | 7tok/sQ4_K_M | 30tok/sQ4_K_M |
| Kimi VL A3B Thinking 2506 | won't run | 86tok/sQ4_K_M |
| Qwen 3.8 27B | won't run | offload |
| Qwen 3.6 27B | won't run | offload |
| Gemma 4 31B | won't run | offload |
| Qwen 3.5 27B | won't run | offload |
| Qwen 3.6 35B-A3B | won't run | offload |
| Gemma 4 26B-A4B | won't run | offload |
| Devstral Small 2 24B | won't run | offload |
| GLM 4.7 Flash | won't run | offload |
| Qwen 3.5 35B-A3B | won't run | offload |
| Nemotron 3.5 Lightning 30B-A3B | won't run | offload |
| Kimi Linear 48B-A3B | won't run | offload |
| Qwen3 Coder 30B-A3B | won't run | offload |
| gpt-oss 20B | won't run | offload |
| Qwen3 32B | won't run | offload |
| DeepSeek R1 Distill Qwen 32B | won't run | offload |
| Gemma 3 27B | won't run | offload |
| Mistral Small 3.2 24B | won't run | offload |
| Devstral Small 2507 | won't run | offload |
| GLM 4.1V 9B Thinking | won't run | offload |
| Kimi VL A3B | won't run | offload |
| LFM2.5 24B A2B | won't run | offload |
| Magistral Small 2506 | won't run | offload |
| Magistral Small 2507 | won't run | offload |
| Magistral Small 2509 | won't run | offload |
| Muse Glimmer 30B | won't run | offload |
| Qwen3.8 27B OBLITERATED | won't run | offload |
| granite 4.2 30b | won't run | offload |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Qwen 3.5 122B-A10B | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| Qwen3 Coder Next | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| Mistral Small 4 119B | won't run | won't run |
| GLM 4.5 Air | won't run | won't run |
| Qwen3 Next 80B-A3B | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |
| DeepSeek R1 | won't run | won't run |
| DeepSeek R1 0528 | won't run | won't run |
| DeepSeek R1 Distill Llama 70B | won't run | won't run |
| DeepSeek R1 Zero | won't run | won't run |
| DeepSeek V3 | won't run | won't run |
| DeepSeek V3 0324 | won't run | won't run |
| DeepSeek V3.1 | won't run | won't run |
| DeepSeek V3.1 Terminus | won't run | won't run |
| DeepSeek V3.2 | won't run | won't run |
| DeepSeek V4 Flash 0731 | won't run | won't run |
| DeepSeek V4 Flash Vision Exp | won't run | won't run |
| Devstral 2 123B Instruct 2512 | won't run | won't run |
| GLM 4.5 | won't run | won't run |
| GLM 4.5V | won't run | won't run |
| GLM 4.6 | won't run | won't run |
| GLM 4.6V | won't run | won't run |
| GLM 4.7 | won't run | won't run |
| GLM 5 | won't run | won't run |
| GLM 5.1 | won't run | won't run |
| GLM 5.2 | won't run | won't run |
| GLM 5.3 | won't run | won't run |
| Kimi Dev 72B | won't run | won't run |
| Kimi K2 | won't run | won't run |
| Kimi K2 Instruct 0905 | won't run | won't run |
| Kimi K2 Thinking | won't run | won't run |
| Kimi K2.5 | won't run | won't run |
| MiniMax M2 | won't run | won't run |
| MiniMax M2.1 | won't run | won't run |
| MiniMax M2.5 | won't run | won't run |
| MiniMax M3 | won't run | won't run |
| Mistral Medium 3.5 128B | won't run | won't run |
Questions
- Which is better for local AI, the Mac mini M4 16GB or the NVIDIA GeForce RTX 4070?
- Choose the NVIDIA GeForce RTX 4070 to run bigger models. Choose the NVIDIA GeForce RTX 4070 for speed. Choose the NVIDIA GeForce RTX 4070 to spend less.
- Which can run bigger models, the Mac mini M4 16GB or the NVIDIA GeForce RTX 4070?
- At 8k context the NVIDIA GeForce RTX 4070 runs 34 of the models we track fully in memory and the Mac mini M4 16GB 33; only the NVIDIA GeForce RTX 4070 holds Kimi VL A3B Thinking 2506.
- Which is faster for local AI, the Mac mini M4 16GB or the NVIDIA GeForce RTX 4070?
- On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 4.0× as fast as the Mac mini M4 16GB (estimated, median across models).
- What is the price difference between the Mac mini M4 16GB and the NVIDIA GeForce RTX 4070?
- In Germany the Mac mini M4 16GB costs 750 € at eBay and the NVIDIA GeForce RTX 4070 700 € at eBay: the NVIDIA GeForce RTX 4070 is 50 € cheaper.
More comparisons
- Intel Arc A770 16GB vs Mac mini M4 16GB
- Intel Arc A770 16GB vs NVIDIA GeForce RTX 4070
- Intel Arc B580 vs NVIDIA GeForce RTX 4070
- Intel Arc Pro B60 vs Mac mini M4 16GB
- Mac mini M4 16GB vs Mac mini M4 32GB
- Mac mini M4 16GB vs Mac mini M4 Pro 48GB
- Mac mini M4 16GB vs NVIDIA GeForce RTX 3080 10GB
- Mac mini M4 16GB vs NVIDIA GeForce RTX 4060 Ti 16GB
- Mac mini M4 16GB vs NVIDIA GeForce RTX 4070 Super
- Mac mini M4 16GB vs NVIDIA GeForce RTX 5060 Ti 16GB