Apple M2 Pro (32GB)
The Apple M2 Pro (32GB) has 32 GB VRAM and 200 GB/s memory bandwidth. It can run 44 of our 80 tracked models natively in VRAM at 8k context.
With 32 GB LPDDR5, the Apple M2 Pro (32GB) is a laptop-tier GPU that can run 44 models natively. It handles 70B-class models at Q4 quantization.
Apple M2 Pro (32GB): 32GB LPDDR5 at 200 GB/s. 12-core CPU (8P+4E).
14B at Q4 native. ~5-8 t/s for 7B.
Full support.
| Vendor | Apple |
| Architecture | Apple M2 Pro |
| CPU cores | 12 (8P + 4E) |
| VRAM | 32 GB (unified) |
| Memory type | LPDDR5 |
| Memory bandwidth | 200 GB/s |
| Compute backend | METAL |
| Tier | Laptop |
| Released | 2023 |
| Models (native) | 44 / 80 |
| Models (offload) | 0 / 80 |
Software: MLX gives the best performance on Apple Silicon; llama.cpp Metal backend is a solid alternative. Both are well-supported by Ollama.
Popular models for this GPU
Models this GPU runs natively in VRAM (44)
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q2_K · ~9.2 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2Q3_K_M · ~28.5 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q3_K_M · ~8.4 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q3_K_M · ~8.6 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5Q4_K_M · ~7.5 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q3_K_M · ~9 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q3_K_M · ~9 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q3_K_M · ~9 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q4_K_M · ~24.5 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q3_K_M · ~8.8 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q4_K_M · ~23.2 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q4_K_M · ~8.1 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q5_K_M · ~7.7 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q5_K_M · ~7.7 t/s
- Bonsai 27B27B · MMLU-Pro 81.5Ternary (Q2_0) · ~18.2 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q5_K_M · ~15.3 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q6_K · ~7.6 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q6_K · ~8 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q6_K · ~14.1 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q8_0 · ~9.4 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q8_0 · ~9.3 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q8_0 · ~9.9 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q8_0 · ~11.2 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6Q8_0 · ~11.4 t/s
- Gemma 4 12B (Unified)12B · MMLU-Pro 77.2Q8_0 · ~10 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0BF16 · ~7.5 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3BF16 · ~9.4 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0BF16 · ~9.4 t/s
- Qwen3 8B8B · MMLU-Pro 56.7BF16 · ~9.3 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3BF16 · ~10.2 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0BF16 · ~10.3 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~9.7 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~9.4 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~8.7 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~11.6 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~12.6 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~14.2 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~19 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~19 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~25.7 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~30.6 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~37 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~76.2 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~90.1 t/s
Too large for this GPU (36)
- Llama 3.3 70B Instruct
- Qwen 2.5 72B Instruct
- DeepSeek R1 Distill Llama 70B
- Command-R 35B
- Llama 3.1 70B Instruct
- Mixtral 8x22B Instruct v0.1
- Llama 3.1 405B Instruct
- DeepSeek V3 671B
- DeepSeek R1 671B
- Llama 4 Scout 109B
- Llama 4 Maverick 400B
- Qwen3 235B-A22B (MoE)
- MiniMax M1 456B
- GPT-OSS 120B
- GLM-4.5 355B
- GLM-4.5 Air 106B
- GLM-4.6 355B
- GLM-4.6V 106B
- GLM-4.7 358B
- Qwen 3.5 122B-A10B (MoE)
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Nemotron 3 Super 120B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
- GLM-5.2 753B
- Nemotron 3 Ultra 550B-A55B
- Step 3.5 Flash
- Step 3.7 Flash
- MiMo V2.5 Pro
- Kimi K2.5
- MiniMax M3
- Inkling
Frequently asked questions
- How much VRAM does the Apple M2 Pro (32GB) have?
- The Apple M2 Pro (32GB) has 32 GB of LPDDR5 with 200 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
- What is the Apple M2 Pro (32GB) best for?
- With 32 GB of VRAM, the Apple M2 Pro (32GB) is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
- What LLMs can the Apple M2 Pro (32GB) run locally?
- The Apple M2 Pro (32GB) can run 44 of the 80 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.
- Can the Apple M2 Pro (32GB) run Llama 3.3 70B Instruct?
- The Apple M2 Pro (32GB) does not have enough VRAM to run Llama 3.3 70B Instruct. You would need more VRAM or a lower quantization level.
- Can the Apple M2 Pro (32GB) run Qwen 3.6 27B?
- Yes. The Apple M2 Pro (32GB) runs Qwen 3.6 27B natively in VRAM at Q5_K_M quantization, achieving approximately 7.7 tokens per second.
- Can the Apple M2 Pro (32GB) run Llama 3.1 8B Instruct?
- Yes. The Apple M2 Pro (32GB) runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 9.4 tokens per second.