▸ DEVICE UNDER TEST
Apple M2 Pro (32GB) — 32 GB VRAM.
▸ APPLE M2 PRO (32GB) SPEC
- BRAND
- Apple
- VRAM
- 32 GB LPDDR5
- BANDWIDTH
- 200 GB/s
- FP16 COMPUTE
- 13.6 TFLOPS
- FP32 COMPUTE
- 13.6 TFLOPS
- TDP
- 30 W
- ARCHITECTURE
- M2 Pro
- MSRP
- $1499
▸ AI CAPABILITY
255/ 331 models @ Q4
With 32 GB VRAM and 200 GB/s bandwidth, this GPU handles models up to 41.9B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~23 tok/s.
§ 01TOP MODELS FOR APPLE M2 PRO (32GB)
255 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| Phi-3.5 MoE 42B | 41.9B | 26.1 GB | 27 | 56.7 |
| Falcon 40B | 40B | 24.9 GB | 4 | 20.9 |
| Qwen3.5-35B-A3B | 36B | 22.5 GB | 5 | 48.5 |
| c4ai-command-r-v01 35B | 35B | 21.9 GB | 5 | 27.5 |
| Qwen 3.5 35B A3B | 35B | 21.9 GB | 59 | 53.3 |
| Qwen 3.6 35B A3B | 35B | 21.9 GB | 59 | 62.7 |
| Nous Capybara 34B | 34.4B | 21.5 GB | 5 | 42.0 |
| Yi-1.5 34B | 34.4B | 21.5 GB | 5 | 45.3 |
| Falcon-H1 34B | 34B | 21.3 GB | 5 | 66.1 |
| CodeLlama 34B | 34B | 21.3 GB | 5 | 25.4 |
| Nous Hermes 2 34B | 34B | 21.3 GB | 5 | 47.0 |
| Phind CodeLlama 34B | 34B | 21.3 GB | 5 | 68.1 |
| LLaVA-1.6 Yi 34B | 34B | 21.3 GB | 5 | 47.4 |
| WizardCoder Python 34B | 34B | 21.3 GB | 5 | 73.2 |
| Yi 34B | 34B | 21.3 GB | 5 | 33.4 |
| DeepSeek Coder 33B | 33B | 20.7 GB | 5 | 26.0 |
| Vicuna 33B | 33B | 20.7 GB | 5 | 17.2 |
| LLaMA 1 30B | 33B | 20.7 GB | 5 | 17.8 |
| DeepSeek-R1-Distill-Qwen-32B | 32.8B | 20.5 GB | 5 | 46.9 |
| Qwen3 32B | 32.8B | 20.5 GB | 5 | 54.9 |