Mac mini M4 32GB vs NVIDIA RTX PRO 4000 Blackwell
For running models locally, priced in the UK. At 128k context the first runs 28 models fully in memory, the second 32.
In short
The Mac mini M4 32GB has more memory for models: 32 GB against 24 GB. At 128k context the NVIDIA RTX PRO 4000 Blackwell runs 32 of the models we track fully in memory and the Mac mini M4 32GB 28; only the NVIDIA RTX PRO 4000 Blackwell holds Ministral 3 8B. On the models both run fully in memory, the NVIDIA RTX PRO 4000 Blackwell is about 5.4× as fast as the Mac mini M4 32GB (estimated, median across models). In the UK the Mac mini M4 32GB costs £1,799 at eBay (used) and the NVIDIA RTX PRO 4000 Blackwell £2,353 at eBay: the Mac mini M4 32GB is £554 cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Mac mini M4 32GB | NVIDIA RTX PRO 4000 Blackwell |
|---|---|---|
| Chip | Apple M4 (10-core GPU) | – |
| Memory bus | 128-bit | 192-bit |
| Memory bandwidth | 120 GB/s | 672 GB/s |
| FP16 compute | 3.76 TFLOPS | 46.9 TFLOPS |
| Software | Metal | CUDA |
| Unified memory | 32 GB | – |
| GPU can use by default | 21.3 GB | – |
| GPU can use, tuned | 24 GB | – |
| Operating system | macos | – |
| Processor | M4 10-core | – |
| Storage | 512 GB | – |
| GPU | – | RTX PRO 4000 Blackwell |
| Memory | – | 24 GB GDDR7 |
| Board power | – | 145 W |
| PCIe generation | – | Gen 5 |
| PCIe lanes | – | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Mac mini M4 32GB | NVIDIA RTX PRO 4000 Blackwell |
|---|---|---|
| Gemma 4 26B-A4B | 9tok/sQ4_K_M | 43tok/sQ5_K_M |
| gpt-oss 20B | 8tok/sMXFP4 | 44tok/sMXFP4 |
| Gemma 4 12B | 5tok/sQ8_0 | 28tok/sQ8_0 |
| Qwen 3.5 9B | 6tok/sQ8_0 | 30tok/sQ8_0 |
| Qwen 3.5 4B | 9tok/sQ8_0 | 47tok/sQ8_0 |
| Ministral 3 8B | won't run | 18tok/sQ4_K_M |
| Gemma 4 E4B | 7tok/sQ8_0 | 35tok/sQ8_0 |
| LFM2.5 8B-A1B | 6tok/sQ8_0 | 33tok/sQ8_0 |
| Llama 3.1 8B | won't run | 18tok/sQ5_K_M |
| Qwen2.5 0.5B | 36tok/sQ8_0 | 195tok/sQ8_0 |
| Qwen3.5 0.8B | 32tok/sQ8_0 | 171tok/sQ8_0 |
| Qwen3.5 2B | 26tok/sQ5_K_M | 136tok/sQ5_K_M |
| LFM3 1.7B | 23tok/sQ8_0 | 120tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 1.5B | 14tok/sQ8_0 | 74tok/sQ8_0 |
| Mellum2.1 12B A2.5B Thinking | 10tok/sQ8_0 | 55tok/sQ8_0 |
| Spark X2.5 4B | 10tok/smlx-4bit | 53tok/smlx-4bit |
| MiniCPM5 2B | 9tok/sQ8_0 | 50tok/sQ8_0 |
| FrogNano 4B 2609 | 9tok/sQ8_0 | 47tok/sQ8_0 |
| Kimi VL A3B | 7tok/smlx-6bit | 34tok/smlx-8bit |
| LFM2.5 2.6B | 7tok/sQ8_0 | 38tok/sQ8_0 |
| LFM2.5 VL 3B | 7tok/sQ8_0 | 38tok/sQ8_0 |
| Kimi VL A3B Thinking 2506 | 7tok/sQ8_0 | 35tok/sQ8_0 |
| GLM 4 9B 0414 | 6tok/smlx-5bit | 31tok/smlx-5bit |
| granite vision 4.1 4b | 5tok/sQ8_0 | 29tok/sQ8_0 |
| granite 4.2 3b | 5tok/sQ8_0 | 29tok/sQ8_0 |
| GLM 4.6V Flash | 5tok/sQ8_0 | 27tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 7B | 5tok/sQ8_0 | 27tok/sQ8_0 |
| GLM 4.1V 9B Thinking | 5tok/smlx-8bit | 24tok/smlx-8bit |
| Ministral 3 3B Instruct 2512 | 4tok/sQ8_0 | 24tok/sQ8_0 |
| Muse Glimmer 30B | 4tok/sQ4_K_M | 19tok/sQ5_K_M |
| DeepSeek R1 Distill Llama 8B | won't run | 18tok/sQ5_K_M |
| Ministral 3 8B Reasoning 2512 | won't run | 18tok/sQ4_K_M |
| Qwen 3.8 27B | won't run | offload |
| Qwen 3.5 122B-A10B | won't run | offload |
| Qwen 3.6 27B | won't run | offload |
| Gemma 4 31B | won't run | offload |
| Mistral Small 4 119B | won't run | offload |
| Qwen 3.5 27B | won't run | offload |
| Qwen 3.6 35B-A3B | 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 |
| Gemma 3 27B | won't run | offload |
| Mistral Small 3.2 24B | won't run | offload |
| Ministral 3 14B | won't run | offload |
| Qwen3 14B | won't run | offload |
| DeepSeek R1 0528 Qwen3 8B | won't run | offload |
| Phi-4 14B | won't run | offload |
| Qwen3 8B | won't run | offload |
| Granite 4.2 8B | won't run | offload |
| DeepSeek R1 Distill Qwen 14B | won't run | offload |
| Devstral Small 2507 | 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 |
| Ministral 3 14B Reasoning 2512 | won't run | offload |
| Qwen3.8 27B OBLITERATED | 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 |
| 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 |
| GLM 4.5 Air | won't run | won't run |
| Qwen3 Next 80B-A3B | won't run | won't run |
| Qwen3 32B | won't run | won't run |
| DeepSeek R1 Distill Qwen 32B | 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 |
| granite 4.2 30b | won't run | won't run |
Questions
- Which is better for local AI, the Mac mini M4 32GB or the NVIDIA RTX PRO 4000 Blackwell?
- Choose the NVIDIA RTX PRO 4000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 4000 Blackwell for speed. Choose the Mac mini M4 32GB to spend less.
- Which can run bigger models, the Mac mini M4 32GB or the NVIDIA RTX PRO 4000 Blackwell?
- At 128k context the NVIDIA RTX PRO 4000 Blackwell runs 32 of the models we track fully in memory and the Mac mini M4 32GB 28; only the NVIDIA RTX PRO 4000 Blackwell holds Ministral 3 8B.
- Which is faster for local AI, the Mac mini M4 32GB or the NVIDIA RTX PRO 4000 Blackwell?
- On the models both run fully in memory, the NVIDIA RTX PRO 4000 Blackwell is about 5.4× 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 RTX PRO 4000 Blackwell?
- In the UK the Mac mini M4 32GB costs £1,799 at eBay (used) and the NVIDIA RTX PRO 4000 Blackwell £2,353 at eBay: the Mac mini M4 32GB is £554 cheaper.
More comparisons
- Intel Arc Pro B60 vs NVIDIA RTX PRO 4000 Blackwell
- Intel Arc Pro B70 vs Mac mini M4 32GB
- Intel Arc Pro B70 vs NVIDIA RTX PRO 4000 Blackwell
- Framework Desktop Ryzen AI Max+ 395 64GB vs Mac mini M4 32GB
- Mac mini M4 16GB vs Mac mini M4 32GB
- Mac mini M4 32GB vs Mac mini M4 Pro 48GB
- Mac mini M4 32GB vs Mac mini M4 Pro 64GB
- Mac mini M4 32GB vs Mac Studio M4 Max 64GB
- Mac mini M4 32GB vs AMD Radeon AI PRO R9700
- Mac mini M4 32GB vs NVIDIA GeForce RTX 3090