← Back to comparison
APPLE
Mac Mini M4 24GB
M4 · M4 · ACTIVE
We earn commissions from purchases made through links on this site. This doesn't affect our rankings or recommendations.
Prices updated 5 days ago
Specifications
| VRAM | 24 GB |
| Memory type | Unified |
| Memory bandwidth | 120 GB/s |
| CPU cores | 10 |
| GPU cores | 10 |
| TDP | 65W |
| Form factor | Mac Mini |
| Max model (Q4) | ~44B parameters |
Inference Benchmarks (Q4_K_M)
Llama 3.3 8B
28.0 tok/s
Qwen 3 32B
—
Llama 3.3 70B
—
llama.cpp, batch_size=1, ctx=4096, single GPU.
What Can You Run?
| Model | Q4_K_M | Q8_0 | FP16 |
|---|---|---|---|
| Llama 3.3 8B8B | Good~28 tok/s | Usable | Usable |
| Llama 3.3 70B70.6B | Won't fit | Won't fit | Won't fit |
| Qwen 3 8B8.2B | Usable | Usable | Usable |
| Qwen 3 32B32.8B | Usable | Won't fit | Won't fit |
| DeepSeek R1 70B70.6B | Won't fit | Won't fit | Won't fit |
| Mistral Nemo 12B12.2B | Usable | Usable | Won't fit |
| Phi-4 14B14B | Usable | Usable | Won't fit |
| Gemma 3 27B27.4B | Usable | Won't fit | Won't fit |
| Codestral 25B25.3B | Usable | Won't fit | Won't fit |
| Command R 35B35B | Usable | Won't fit | Won't fit |
Notes
Entry-level Apple Silicon. ~18GB usable for LLM after OS overhead.