Mac mini M4 Pro 24GB
Apple · M4 Pro · 24GB Unified Memory · Can run 20 models
| Manufacturer | Apple |
| Unified Memory | 24 GB |
| Chip | M4 Pro |
| CPU Cores | 14 |
| GPU Cores | 20 |
| Neural Engine Cores | 16 |
| Memory Bandwidth | 273 GB/s |
| MSRP | $1,399 |
| Released | Nov 8, 2024 |
AI Notes
The Mac mini M4 Pro 24GB provides a significant step up in AI performance with 273 GB/s memory bandwidth. With 24GB of unified memory, it can run 13B models at full precision and 30B models with quantization. The M4 Pro chip's higher bandwidth delivers noticeably faster token generation than the base M4.
Compatible Models
| Model | Parameters | Best Quant | VRAM Used | Fit |
|---|---|---|---|---|
| Llama 3.2 1B | 1B | Q8_0 | 3 GB | Runs |
| Gemma 2 2B | 2B | Q8_0 | 4 GB | Runs |
| Llama 3.2 3B | 3B | Q8_0 | 5 GB | Runs |
| Phi-3 Mini 3.8B | 3.8B | Q8_0 | 5.8 GB | Runs |
| DeepSeek R1 7B | 7B | Q8_0 | 9 GB | Runs |
| Mistral 7B | 7B | Q8_0 | 9 GB | Runs |
| Qwen 2.5 7B | 7B | Q8_0 | 9 GB | Runs |
| Qwen 2.5 Coder 7B | 7B | Q8_0 | 9 GB | Runs |
| Llama 3.1 8B | 8B | Q8_0 | 10 GB | Runs |
| Gemma 2 9B | 9B | Q8_0 | 11 GB | Runs |
| DeepSeek R1 14B | 14B | Q4_K_M | 9.9 GB | Runs |
| Phi-4 14B | 14B | Q4_K_M | 9.9 GB | Runs |
| Qwen 2.5 14B | 14B | Q4_K_M | 9.9 GB | Runs |
| StarCoder2 15B | 15B | Q8_0 | 17 GB | Runs |
| Codestral 22B | 22B | Q4_K_M | 14.7 GB | Runs |
| Gemma 2 27B | 27B | Q4_K_M | 17.7 GB | Runs |
| DeepSeek R1 32B | 32B | Q4_K_M | 20.7 GB | Runs (tight) |
| Qwen 2.5 32B | 32B | Q4_K_M | 20.7 GB | Runs (tight) |
| Command R 35B | 35B | Q4_K_M | 22.5 GB | Runs (tight) |
| Mixtral 8x7B | 47B | Q4_K_M | 29.7 GB | CPU Offload |
5
model(s) are too large for this hardware.