M3 16GB
Apple Silicon
16GB VRAM · 100 GB/s bandwidth · 8.2 FP16 TFLOPS · 15W TDP · $899 street price
The M3 16GB has 16GB of VRAM. With only 16GB available, no current reference LLMs fit comfortably at Q4 quantization. Consider GPUs with 12GB+ VRAM for local inference.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | tight | 21 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | tight | 11 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | tight | 10 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | tight | 3 tok/s |
| Gemma 3 27B | 27.4B | 14 GB | won't fit | |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | won't fit | |
| Llama 3.3 70B | 70.6B | 35 GB | won't fit | |
| Qwen 2.5 72B | 72.7B | 36 GB | won't fit | |
| Llama 3.1 405B | 405B | 202 GB | won't fit | |
| DeepSeek R1 671B | 671B | 336 GB | won't fit |
Similar GPUs
| GPU | VRAM | BW | TFLOPS | TDP |
|---|---|---|---|---|
| M2 16GB | 16GB | 100 GB/s | 7.2 | 15W |
| M4 16GB | 16GB | 120 GB/s | 9.2 | 20W |
| M1 16GB | 16GB | 68 GB/s | 5.2 | 15W |
| M1 Pro 16GB | 16GB | 200 GB/s | 10.6 | 30W |
| M2 Pro 16GB | 16GB | 200 GB/s | 13.6 | 30W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.