Mac mini M4 32GB
Apple · M4 · 32GB Unified Memory · Can run 24 models
| Manufacturer | Apple |
| Unified Memory | 32 GB |
| Chip | M4 |
| CPU Cores | 10 |
| GPU Cores | 10 |
| Neural Engine Cores | 16 |
| Memory Bandwidth | 120 GB/s |
| MSRP | $799 |
| Released | Nov 8, 2024 |
AI Notes
The Mac mini M4 32GB doubles the memory of the base model, enabling much larger AI workloads. With 32GB of unified memory, it can run 13B models at full precision and 30B models with quantization. At $799, it offers exceptional value as a compact local AI inference machine.
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 |
| Qwen 2.5 32B | 32B | Q4_K_M | 20.7 GB | Runs |
| Command R 35B | 35B | Q4_K_M | 22.5 GB | Runs |
| Mixtral 8x7B | 47B | Q4_K_M | 29.7 GB | Runs (tight) |
| DeepSeek R1 70B | 70B | Q4_K_M | 43.5 GB | CPU Offload |
| Llama 3.1 70B | 70B | Q4_K_M | 43.5 GB | CPU Offload |
| Llama 3.3 70B | 70B | Q4_K_M | 43.5 GB | CPU Offload |
| Qwen 2.5 72B | 72B | Q4_K_M | 44.7 GB | CPU Offload |
1
model(s) are too large for this hardware.