Apple silicon (unified memory)
What AI models can the Apple M5 Max (40-core GPU) run locally?
At 4-bit quantization with an 8K-token conversation, 84 of the 146 open-weight models in our directory fit entirely in the Apple M5 Max (40-core GPU)'s 128 GB of unified memory (about 96 GB usable, the default GPU share, often adjustable), up to Ling 3.0 Flash. Among models of 7B parameters or more, Laguna XS 2.1 (free) is the fastest, at an estimated 164 to 212 tokens per second.
| Model | Parameters | Memory needed | Estimated speed |
|---|---|---|---|
| Runs entirely in fast memory (84) | |||
| Ling 3.0 Flash Inclusionai | 127B 8.6B active | 78 GB 77 GB + 0.4 GB cache | 47–61 tokens/s Fast |
| Ling 3.0 Flash Inclusionai | 127B 8.6B active | 78 GB 77 GB + 0.4 GB cache | 47–61 tokens/s Fast |
| Qwen3.5 122B-A10B Alibaba (Qwen) | 125B 12.7B active | 77 GB 76 GB + 0.2 GB cache | 33–42 tokens/s Fast |
| Ling 3.0 Flash VL Inclusionai | 125B 5.9B active | 77 GB 76 GB + 0.4 GB cache | 67–87 tokens/s Fast |
| Ling 3.0 Flash VL Inclusionai | 125B 5.9B active | 77 GB 76 GB + 0.4 GB cache | 67–87 tokens/s Fast |
| Nemotron Super NVIDIA | 124B | 76 GB 75 GB + 0.1 GB cache | Speed not estimated for this architecture |
| Laguna S 2.1 (free) Poolside | 118B 6.1B active | 73 GB 71 GB + 0.5 GB cache | 65–84 tokens/s Fast |
| OpenAI GPT 120B OpenAI | 117B 5.8B active | 72 GB 71 GB + 0.3 GB cache | 70–91 tokens/s Fast |
| GLM-4.5-Air Zhipu AI (Z.ai) | 110B 17.0B active | 69 GB 67 GB + 1.5 GB cache | 23–30 tokens/s Comfortable to read |
| Llama 4 Scout Meta | 109B | 67 GB weights only | Speed not estimated (architecture not public) |
| GLM-4.6V Zhipu AI (Z.ai) | 108B 14.3B active | 68 GB 65 GB + 1.5 GB cache | 27–35 tokens/s Fast |
| GLM-4.5V Zhipu AI (Z.ai) | 108B 14.3B active | 68 GB 65 GB + 1.5 GB cache | 27–35 tokens/s Fast |
| Qwen3-Next 80B-A3B Instruct Alibaba (Qwen) | 81.3B 5.5B active | 51 GB 49 GB + 0.8 GB cache | 68–88 tokens/s Fast |
| Qwen3-Next 80B-A3B (Thinking) Alibaba (Qwen) | 81.3B 5.5B active | 51 GB 49 GB + 0.8 GB cache | 68–88 tokens/s Fast |
| Hunyuan A13B Instruct Tencent (Hunyuan) | 80.4B | 51 GB 49 GB + 1.1 GB cache | Speed not estimated for this architecture |
| Qwen3 Coder Next Alibaba (Qwen) | 79.7B 3.9B active | 50 GB 48 GB + 0.8 GB cache | 93–120 tokens/s Fast |
| Qwen2.5-VL 72B Instruct Alibaba (Qwen) | 73.4B | 48 GB 45 GB + 2.7 GB cache | 5.6–7.2 tokens/s Usable but slow |
| Qwen2.5 72B Instruct Alibaba (Qwen) | 72.7B | 48 GB 44 GB + 2.7 GB cache | 5.6–7.3 tokens/s Usable but slow |
| Magnum v4 72B Anthracite ORG | 72.7B | 48 GB 44 GB + 2.7 GB cache | 5.6–7.3 tokens/s Usable but slow |
| Hermes 3 70B Instruct Nousresearch | 70.6B | 46 GB 43 GB + 2.7 GB cache | 5.8–7.5 tokens/s Usable but slow |
| Hermes 3 70B Instruct Nousresearch | 70.6B | 46 GB 43 GB + 2.7 GB cache | 5.8–7.5 tokens/s Usable but slow |
| Llama-3.3-70B-Instruct Meta | 70.6B | 44 GB weights only | Speed not estimated (architecture not public) |
| Llama-3.1-70B-Instruct Meta | 70.6B | 44 GB weights only | Speed not estimated (architecture not public) |
| Skyfall 36B V2 Thedrummer | 36.9B | 25 GB 22 GB + 2.1 GB cache | 11–14 tokens/s Comfortable to read |
| Qwen3.5 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 86–112 tokens/s Fast |
| Qwen3.6 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 86–112 tokens/s Fast |
| Nex-N2.5-Mini NEX AGI | 35.1B 3.9B active | 22 GB 21 GB + 0.2 GB cache | 104–135 tokens/s Fast |
| Laguna XS 2.1 (free) Poolside | 33.4B 2.2B active | 21 GB 20 GB + 0.4 GB cache | 164–212 tokens/s Fast |
| Qwen3 VL 32B Instruct Alibaba (Qwen) | 33.4B | 23 GB 20 GB + 2.1 GB cache | 12–16 tokens/s Comfortable to read |
| Qwen2.5 Coder 32B Instruct Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 12–16 tokens/s Comfortable to read |
| Qwen3 32B Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 12–16 tokens/s Comfortable to read |
| Nemotron 3 Nano 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.1 GB cache | Speed not estimated for this architecture |
| Nemotron 3.5 Lightning 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.4 GB cache | Speed not estimated for this architecture |
| Gemma 4 31B IT Google DeepMind | 31.3B | 22 GB 19 GB + 2.2 GB cache | 13–16 tokens/s Comfortable to read |
| GLM-4.7-Flash Zhipu AI (Z.ai) | 31.2B 5.2B active | 20 GB 19 GB + 0.4 GB cache | 76–98 tokens/s Fast |
| Qwen3 VL 30B A3B Instruct Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 92–120 tokens/s Fast |
| Qwen3 VL 30B A3B Thinking Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 92–120 tokens/s Fast |
| Qwen3-Coder 30B-A3B Instruct Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 105–136 tokens/s Fast |
| Qwen3 30B A3B Instruct 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 105–136 tokens/s Fast |
| Qwen3 30B A3B Thinking 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 105–136 tokens/s Fast |
| Qwen3 30B A3B Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 105–136 tokens/s Fast |
| Hy-MT2-30B-A3B Tencent (Hunyuan) | 30.1B 3.5B active | 20 GB 18 GB + 0.8 GB cache | 102–132 tokens/s Fast |
| Muse Glimmer 30B Meta | 29.8B | 19 GB 18 GB + 0.2 GB cache | 14–18 tokens/s Comfortable to read |
| Qwen3.8 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 15–19 tokens/s Comfortable to read |
| Qwen3.5 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 15–19 tokens/s Comfortable to read |
| Qwen3.6 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 15–19 tokens/s Comfortable to read |
| Gemma 3 27B IT Google DeepMind | 27.4B | 17 GB weights only | Speed not estimated (architecture not public) |
| Gemma 2 27B Google DeepMind | 27.2B | 17 GB weights only | Speed not estimated (architecture not public) |
| Gemma 4 26B A4B IT Google DeepMind | 25.8B | 17 GB 16 GB + 0.5 GB cache | Speed not estimated for this architecture |
| Voxtral Small 24B 2507 Mistral AI | 24.3B | 17 GB 15 GB + 1.3 GB cache | 17–21 tokens/s Comfortable to read |
| Uncensored Cognitivecomputations | 24.0B | 17 GB 15 GB + 1.3 GB cache | 17–22 tokens/s Comfortable to read |
| Mistral Small 3.1 24B Instruct Mistral AI | 24.0B | 17 GB 15 GB + 1.3 GB cache | 17–22 tokens/s Comfortable to read |
| LFM2.5-24B-A2B Liquid | 24.0B | 16 GB 15 GB + 0.2 GB cache | Speed not estimated for this architecture |
| Mistral Small 3 Mistral AI | 23.6B | 16 GB 14 GB + 1.3 GB cache | 17–22 tokens/s Comfortable to read |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 17–22 tokens/s Comfortable to read |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 17–22 tokens/s Comfortable to read |
| Safety GPT OSS 20B OpenAI | 21.5B 4.8B active | 14 GB 13 GB + 0.2 GB cache | 85–110 tokens/s Fast |
| GPT OSS 20B OpenAI | 20.9B 4.2B active | 14 GB 13 GB + 0.2 GB cache | 97–125 tokens/s Fast |
| Reka Flash 3 Rekaai | 20.9B | 15 GB 13 GB + 1.1 GB cache | 19–25 tokens/s Comfortable to read |
| Qwen3 14B Alibaba (Qwen) | 14.8B | 11 GB 9.0 GB + 1.3 GB cache | 27–34 tokens/s Fast |
| Phi 4 Microsoft | 14.7B | 11 GB 8.9 GB + 1.7 GB cache | 26–34 tokens/s Fast |
| Ministral 3 14B Mistral AI | 13.9B | 11 GB 8.5 GB + 1.3 GB cache | 28–36 tokens/s Fast |
| Gemma 3 12B IT Google DeepMind | 12.2B | 8.2 GB weights only | Speed not estimated (architecture not public) |
| Llama Guard 4 12B Meta | 12.0B | 8.1 GB weights only | Speed not estimated (architecture not public) |
| Qwen3.5 9B Alibaba (Qwen) | 9.7B | 6.9 GB 5.9 GB + 0.3 GB cache | 43–55 tokens/s Fast |
| Moondream 3.1 Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Moondream 3 Preview Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Ministral 3 8B Mistral AI | 8.9B | 7.3 GB 5.4 GB + 1.1 GB cache | 43–55 tokens/s Fast |
| Granite 4.2 8B IBM | 8.8B | 7.5 GB 5.3 GB + 1.3 GB cache | 43–55 tokens/s Fast |
| Qwen3 VL 8B Instruct Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 43–56 tokens/s Fast |
| Qwen3 VL 8B Thinking Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 43–56 tokens/s Fast |
| UI-TARS 7B Bytedance | 8.3B | 6.3 GB 5.0 GB + 0.5 GB cache | 49–63 tokens/s Fast |
| Qwen3 8B Alibaba (Qwen) | 8.2B | 7.0 GB 5.0 GB + 1.2 GB cache | 46–59 tokens/s Fast |
| Llama 3.1 8B Instruct fp8 Meta | 8.0B | 5.7 GB weights only | Speed not estimated (architecture not public) |
| Hy-MT2-7B Tencent (Hunyuan) | 8.0B | 6.7 GB 4.9 GB + 1.1 GB cache | 47–61 tokens/s Fast |
| Qwen2.5 7B Instruct Alibaba (Qwen) | 7.6B | 5.9 GB 4.6 GB + 0.5 GB cache | 53–68 tokens/s Fast |
| Gemma 3 4B IT Google DeepMind | 4.3B | 3.4 GB weights only | Speed not estimated (architecture not public) |
| Nemotron 3.5 Content Safety (free) NVIDIA | 4.3B | 3.7 GB 2.6 GB + 0.3 GB cache | 93–120 tokens/s Fast |
| Ministral 3 3B Mistral AI | 3.8B | 4.0 GB 2.3 GB + 0.9 GB cache | 92–119 tokens/s Fast |
| Llama 3.2 3B Instruct Meta | 3.2B | 2.7 GB weights only | Speed not estimated (architecture not public) |
| Granite 4.0 Micro IBM | 3.2B | 2.8 GB 1.9 GB + 0.1 GB cache | 130–168 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 170–220 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 170–220 tokens/s Fast |
| Llama 3.2 1B Instruct Meta | 1.2B | 1.5 GB weights only | Speed not estimated (architecture not public) |
62 larger models do not fit. Change the quantization, conversation length or memory size in the tool.
Compared with similar chips
- Apple M5 Pro: 64 GB, 68 models fit entirely (-16); about 29% slower on models that fit both (307 vs 614 GB/s).
- Apple M4 Max (16-core CPU): same memory, so the same models fit; about 6% slower on models that fit both (546 vs 614 GB/s).
- NVIDIA DGX Spark (GB10): same memory, so the same models fit; about 36% slower on models that fit both (273 vs 614 GB/s).
- AMD Ryzen AI Max+ 395: same memory, so the same models fit; about 40% slower on models that fit both (256 vs 614 GB/s).
- Apple M3 Ultra: 512 GB, 119 models fit entirely (+35); about 15% faster on models that fit both (819 vs 614 GB/s).
Frequently asked questions
What is the largest AI model the Apple M5 Max (40-core GPU) can run?
At 4-bit quantization with an 8K-token conversation, the largest model in our directory that fits entirely in its 128 GB of unified memory is Ling 3.0 Flash (78 GB).
Can the Apple M5 Max (40-core GPU) run GPT OSS 20B?
Yes. At 4-bit, GPT OSS 20B needs about 14 GB and fits entirely in the Apple M5 Max (40-core GPU)'s memory at an estimated 97 to 125 tokens per second.
Can the Apple M5 Max (40-core GPU) run Qwen3 32B?
Yes. At 4-bit, Qwen3 32B needs about 23 GB and fits entirely in the Apple M5 Max (40-core GPU)'s memory at an estimated 12 to 16 tokens per second.
Can the Apple M5 Max (40-core GPU) run OpenAI GPT 120B?
Yes. At 4-bit, OpenAI GPT 120B needs about 72 GB and fits entirely in the Apple M5 Max (40-core GPU)'s memory at an estimated 70 to 91 tokens per second.
These are estimates, not measurements: memory from each model's parameter count and published architecture, speed from memory bandwidth, calibrated on the AIPCs test bench. Drivers, software and prompt length move real results. How the estimate works.