Apple M3 Pro (18GB)
The Apple M3 Pro (18GB) has 18GB VRAM and 150 GB/s memory bandwidth. It can run 37 of our 53 tracked models natively in VRAM at 8k context.
18 GB VRAM150 GB/sMETALlaptopUnified memory
Models this GPU runs natively in VRAM (37)
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro —Q2_K · ~183.3 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q2_K · ~14.5 t/s
- Qwen3 32B32.8B · MMLU-Pro —Q2_K · ~15.2 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 55.1Q2_K · ~15.4 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q2_K · ~15.4 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q2_K · ~15.4 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro —Q2_K · ~183.3 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q2_K · ~18.4 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro —Q3_K_M · ~13.9 t/s
- Qwen 3.6 27B27B · MMLU-Pro —Q3_K_M · ~13.9 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro —Q3_K_M · ~108.6 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro —Q3_K_M · ~15.6 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q3_K_M · ~16.9 t/s
- Qwen3 14B14.8B · MMLU-Pro —Q6_K · ~13.5 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 51.2Q5_K_M · ~16.3 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 56.1Q6_K · ~14.3 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q6_K · ~16.4 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro —Q6_K · ~16.4 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0Q8 · ~16.3 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 37.5Q8 · ~18.8 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0Q8 · ~18.8 t/s
- Qwen3 8B8B · MMLU-Pro —Q8 · ~18.8 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 36.5Q8 · ~19.7 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0Q8 · ~20.7 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro —FP16 · ~18.8 t/s
- Gemma 4 E4B4B · MMLU-Pro —FP16 · ~18.8 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 35.6FP16 · ~19.7 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP16 · ~23.4 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP16 · ~24.2 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP16 · ~28.8 t/s
- Gemma 4 E2B2B · MMLU-Pro —FP16 · ~37.5 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP16 · ~44.1 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP16 · ~50 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP16 · ~60.5 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro —FP16 · ~75 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP16 · ~150 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP16 · ~208.3 t/s
Too large for this GPU (16)
- Llama 3.3 70B Instruct
- Qwen 2.5 72B Instruct
- Mixtral 8x7B Instruct v0.1
- 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)
- Gemma 4 31B
- Qwen 3.5 122B-A10B (MoE)
- Kimi K2.6