What Can the Apple M2 Max Run?
96 GB · compatibility with 168 AI models
Short answer: the Apple M2 Max (96 GB) can run 168 of 168 AI image, video, 3D and audio models we track. Best picks: SDXL Base 1.0, SDXL img2img, Stable Diffusion 1.5, SD 1.5 img2img, SD 1.5 Inpainting. Unified memory.
| Perfect | Great | Good | Usable | Barely | Can't Run |
|---|---|---|---|---|---|
| 13 models | 0 models | 36 models | 116 models | 3 models | 0 models |
Apple M2 Max specs for AI
| Brand | Apple |
|---|---|
| Series | M2 |
| VRAM | 96 GB |
| Architecture | m2 |
| FP16 compute | 13.6 TFLOPS |
| Memory bandwidth | 400 GB/s |
| Released | 2023 |
AI models on the Apple M2 Max
Each model uses the best format that fits in 96 GB. How ratings work.
Text to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SDXL Base 1.0 | Good | FP16 | 7 GB | Fast |
| Stable Diffusion 1.5 | Good | FP16 | 4 GB | Fast |
| SDXL Turbo | Good | FP16 | 7 GB | Fast |
| Stable Diffusion 1.4 | Good | FP16 | 4 GB | Fast |
| Stable Diffusion 3.5 Medium (2.5B) | Good | FP16 | 8 GB | Fast |
| Animagine XL 3.1 | Good | FP16 | 7 GB | Fast |
| Pony Diffusion v6 XL | Good | FP16 | 7 GB | Fast |
| NoobAI XL | Good | FP16 | 7 GB | Fast |
| Juggernaut XL Ragnarok | Good | FP16 | 7 GB | Fast |
| SDXL Lightning 4-step | Good | FP16 | 7 GB | Fast |
| DreamShaper XL | Good | FP16 | 7 GB | Fast |
| Illustrious XL v1.0 | Good | FP16 | 7 GB | Fast |
| Playground v2.5 2.6B | Good | FP16 | 7 GB | Fast |
| RealVisXL v5.0 | Good | FP16 | 7 GB | Fast |
| Epicrealism XL | Good | FP16 | 7 GB | Fast |
| PixArt-Sigma 900M | Good | FP16 | 7 GB | Fast |
| Stable Diffusion 2.1 | Good | FP16 | 5 GB | Fast |
| PixArt-Alpha 600M | Good | FP16 | 6 GB | Fast |
| Stable Diffusion 3 Medium (2B) | Good | FP16 | 7 GB | Fast |
| SDXL Hyper 1-step | Good | FP16 | 7 GB | Fast |
| Stable Diffusion 2.0 | Good | FP16 | 5 GB | Fast |
| HunyuanDiT 1.5B | Usable | FP16 | 8 GB | Fast |
| Qwen-Image 2.1 | Usable | FP16 | 14 GB | Fast |
| Z-Image Turbo | Usable | FP16 | 10 GB | Fast |
| MOSS-Image 5B | Usable | FP16 | 12 GB | Fast |
| Flux.2 Klein 4B | Usable | FP16 | 13 GB | Fast |
| Z-Image Base | Usable | FP16 | 14 GB | Fast |
| Ming-Image 0.1 Design | Usable | FP16 | 14 GB | Fast |
| Flux.1 Lite | Usable | FP16 | 12 GB | Fast |
| AuraFlow 0.3 | Usable | FP16 | 12 GB | Fast |
| Kolors | Usable | FP16 | 14 GB | Fast |
| FLUX.2 Klein 9B | Usable | FP16 | 18 GB | Fast |
| Stable Diffusion 3.5 Large (8B) | Usable | FP16 | 18 GB | Fast |
| Stable Diffusion 3.5 Large Turbo | Usable | FP16 | 18 GB | Fast |
| Ideogram 4.0 | Usable | FP16 | 19 GB | Fast |
| ERNIE-Image 8B | Usable | FP16 | 16 GB | Fast |
| Chroma1 HD | Usable | FP16 | 18 GB | Fast |
| HiDream-O1-Image 8.8B | Usable | FP16 | 16 GB | Fast |
| Seedream 3.0 | Usable | FP16 | 16 GB | Fast |
| GLM-Image | Usable | FP16 | 16 GB | Fast |
| HunyuanImage 3.0 | Usable | FP16 | 20 GB | Fast |
| Krea 2 Turbo | Usable | FP16 | 26 GB | Fast |
| Flux.1 Dev 12B | Usable | FP16 | 24 GB | Fast |
| Flux.1 Schnell 12B | Usable | FP16 | 24 GB | Fast |
| FLUX.1 Krea Dev | Usable | FP16 | 24 GB | Fast |
| Qwen-Image 2512 (20B) | Usable | FP16 | 41 GB | Moderate |
| Flux.2 Dev 32B | Barely | FP16 | 64 GB | Moderate |
Image to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SDXL img2img | Good | FP16 | 7 GB | Fast |
| SD 1.5 img2img | Good | FP16 | 4 GB | Fast |
| InstructPix2Pix | Good | FP16 | 5 GB | Fast |
| IP-Adapter FaceID SDXL | Usable | FP16 | 10 GB | Fast |
| IP-Adapter SDXL | Usable | FP16 | 9 GB | Fast |
| Mage-Flow 4B | Usable | FP16 | 10 GB | Fast |
| LongCat-Image Edit | Usable | FP16 | 15 GB | Fast |
| Boogu-Image Edit | Usable | FP16 | 21 GB | Fast |
| Flux.1 Dev img2img 12B | Usable | FP16 | 24 GB | Fast |
| Flux Kontext Dev | Usable | FP16 | 24 GB | Fast |
| Qwen-Image-Edit 2511 | Usable | FP16 | 41 GB | Moderate |
Inpainting
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 Inpainting | Good | FP16 | 4 GB | Fast |
| SDXL Inpainting | Good | FP16 | 7 GB | Fast |
| BrushNet | Usable | FP16 | 8 GB | Fast |
| PowerPaint v2.1 | Usable | FP16 | 7 GB | Fast |
| Flux.1 Fill Dev | Usable | FP16 | 24 GB | Fast |
ControlNet
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| ControlNet SD 1.5 | Good | FP16 | 5 GB | Fast |
| T2I-Adapter SDXL | Usable | FP16 | 8 GB | Fast |
| ControlNet SDXL | Usable | FP16 | 9 GB | Fast |
| ControlNet Flux | Usable | FP16 | 28 GB | Fast |
Video
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| WAN 2.1 T2V 1.3B | Usable | FP16 | 6 GB | Fast |
| Stable Video Diffusion 1.1 | Usable | FP16 | 8 GB | Fast |
| AnimateDiff Lightning | Usable | FP16 | 6 GB | Fast |
| CogVideoX 2B | Usable | FP16 | 8 GB | Fast |
| AnimateDiff v3 (SD 1.5) | Usable | FP16 | 6 GB | Fast |
| ModelScope T2V | Usable | FP16 | 8 GB | Fast |
| ZeroScope v2 576w | Usable | FP16 | 6 GB | Fast |
| TokenFlow | Usable | FP16 | 8 GB | Fast |
| AnimateDiff V2V | Usable | FP16 | 6 GB | Fast |
| Latte | Usable | FP16 | 8 GB | Fast |
| AnimateDiff I2V | Usable | FP16 | 6 GB | Fast |
| SEINE | Usable | FP16 | 8 GB | Fast |
| WAN 2.2 TI2V 5B | Usable | FP16 | 12 GB | Fast |
| LTX-Video 0.9 (2B) | Usable | FP16 | 10 GB | Fast |
| LTX-Video I2V | Usable | FP16 | 10 GB | Fast |
| CogVideoX 5B | Usable | FP16 | 14 GB | Fast |
| CogVideoX 5B I2V | Usable | FP16 | 14 GB | Fast |
| SkyReels V1 | Usable | FP16 | 14 GB | Fast |
| Stable Video Diffusion XT 1.1 (25 frames) | Usable | FP16 | 10 GB | Fast |
| SkyReels V1 I2V | Usable | FP16 | 14 GB | Fast |
| DynamiCrafter 512 | Usable | FP16 | 10 GB | Fast |
| AnimateDiff SDXL | Usable | FP16 | 12 GB | Fast |
| Kandinsky 6.0 Video Lite 3B | Usable | FP16 | 9 GB | Fast |
| Waver 1.0 | Usable | FP16 | 12 GB | Fast |
| DynamiCrafter 1024 | Usable | FP16 | 18 GB | Fast |
| WAN 2.2 T2V A14B (MoE) | Usable | FP16 | 28 GB | Fast |
| WAN 2.2 I2V A14B | Usable | FP16 | 28 GB | Fast |
| WAN 2.1 T2V 14B | Usable | FP16 | 28 GB | Fast |
| WAN 2.1 I2V 480P 14B | Usable | FP16 | 28 GB | Fast |
| WAN 2.1 V2V | Usable | FP16 | 28 GB | Fast |
| HunyuanVideo T2V v1.5 | Usable | FP16 | 28 GB | Fast |
| HunyuanVideo I2V v1.5 | Usable | FP16 | 28 GB | Fast |
| HunyuanVideo 13B T2V | Usable | FP16 | 28 GB | Fast |
| HunyuanVideo I2V | Usable | FP16 | 28 GB | Fast |
| LTX-Video 13B | Usable | FP16 | 28 GB | Fast |
| MOVA | Usable | FP16 | 29 GB | Fast |
| Open-Sora 2.0 (11B) | Usable | FP16 | 24 GB | Fast |
| MAGI-1 | Usable | FP16 | 24 GB | Fast |
| LongCat-Video 13.6B | Usable | FP16 | 27 GB | Fast |
| Ovi 1.1 | Usable | FP16 | 23 GB | Fast |
| SkyReels V3 R2V 14B | Usable | FP16 | 29 GB | Fast |
| Wan 2.2 Animate 14B | Usable | FP16 | 35 GB | Moderate |
| Wan 2.2 S2V 14B | Usable | FP16 | 33 GB | Fast |
| WAN 2.1 I2V 720P 14B | Usable | FP16 | 32 GB | Fast |
| Wan-Animate-2 14B | Usable | FP16 | 33 GB | Fast |
| SCAIL-2 14B | Usable | FP16 | 33 GB | Fast |
| FramePack I2V HY FP8 | Usable | FP16 | 32 GB | Fast |
| Wan-Dancer 14B | Usable | FP16 | 34 GB | Moderate |
| HuMo 17B | Usable | FP16 | 34 GB | Moderate |
| MiniMax H3 FL2VA | Usable | FP16 | 40 GB | Moderate |
| MiniMax H3 Ref2VA | Usable | FP16 | 40 GB | Moderate |
| LTX-2 19B | Usable | FP16 | 38 GB | Moderate |
| Mochi 1 10B | Usable | FP16 | 40 GB | Moderate |
| LTX-2.5 22B | Barely | FP16 | 42 GB | Moderate |
| LTX-2.3 22B | Barely | FP16 | 42 GB | Moderate |
Upscaler
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| 4x-UltraSharp | Perfect | FP32 | 0.3 GB | Fast |
| 4x-Remacri | Perfect | FP32 | 0.3 GB | Fast |
| SwinIR | Perfect | FP32 | 0.5 GB | Fast |
| RealESRGAN x4plus | Perfect | FP32 | 0.3 GB | Fast |
| HAT | Perfect | FP32 | 0.5 GB | Fast |
| DAT | Perfect | FP32 | 0.5 GB | Fast |
| ScuNET | Perfect | FP32 | 0.3 GB | Fast |
| LDSR | Good | FP16 | 4 GB | Fast |
| SeedVR2 3B | Usable | FP16 | 9 GB | Fast |
| SeedVR2 7B | Usable | FP16 | 16 GB | Fast |
Face/Restore
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| GFPGAN v1.4 | Perfect | FP32 | 0.3 GB | Fast |
| CodeFormer v0.1 | Perfect | FP32 | 0.3 GB | Fast |
VAE
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 VAE ft-mse | Perfect | FP32 | 0.2 GB | Fast |
| Flux VAE | Perfect | FP32 | 0.3 GB | Fast |
| SDXL VAE | Perfect | FP32 | 0.3 GB | Fast |
| TAESD / TAESDXL | Perfect | FP32 | 0.1 GB | Fast |
3D
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| TripoSR | Good | FP16 | 4 GB | Fast |
| Shap-E | Good | FP16 | 4 GB | Fast |
| InstantMesh | Usable | FP16 | 6 GB | Fast |
| Zero123++ v1.2 | Usable | FP16 | 6 GB | Fast |
| LGM | Usable | FP16 | 8 GB | Fast |
| One-2-3-45 | Usable | FP16 | 8 GB | Fast |
| Pixal3D | Usable | FP16 | 14 GB | Fast |
| Hunyuan3D 2.0 | Usable | FP16 | 12 GB | Fast |
| Hunyuan3D 2.1 | Usable | FP16 | 10 GB | Fast |
| SV3D | Usable | FP16 | 10 GB | Fast |
| TRELLIS.2 4B | Usable | FP16 | 24 GB | Fast |
| SAM 3D Objects | Usable | FP16 | 32 GB | Fast |
Audio
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| Whisper Large v3 | Good | FP16 | 4 GB | Fast |
| MusicGen Medium (1.5B) | Good | FP16 | 6 GB | Fast |
| MusicGen Small (300M) | Good | FP16 | 2 GB | Fast |
| Bark | Good | FP16 | 8 GB | Fast |
| XTTS v2 | Good | FP16 | 3 GB | Fast |
| Stable Audio Open | Good | FP16 | 4 GB | Fast |
| Qwen3-TTS 1.7B | Usable | FP16 | 5 GB | Fast |
| Chatterbox Multilingual | Usable | FP16 | 4 GB | Fast |
| ACE-Step 1.5 Turbo | Usable | FP16 | 8 GB | Fast |
| VibeVoice 1.5B | Usable | FP16 | 7 GB | Fast |
| Stable Audio 3 Medium | Usable | FP16 | 7 GB | Fast |
| Stable Audio 3 Small-SFX | Usable | FP16 | 3 GB | Fast |
| MMAudio Large 44k | Usable | FP16 | 4 GB | Fast |
| IndexTTS 2.5 | Usable | FP16 | 6 GB | Fast |
| MusicGen Large (3.3B) | Usable | FP16 | 12 GB | Fast |
| YuE2 3B | Usable | FP16 | 24 GB | Fast |
| MiniMax Music 3 | Usable | FP16 | 24 GB | Fast |
| Fish Audio S2 Pro 4B | Usable | FP16 | 24 GB | Fast |
Frequently asked questions
How much VRAM does the Apple M2 Max have?
The Apple M2 Max has 96 GB of unified memory (shared with the CPU) with 400 GB/s of memory bandwidth.
What AI models can the Apple M2 Max run?
It can run 168 of the 168 AI models we track: 13 perfectly (S), 0 great (A), 36 good (B), 116 usable (C) and 3 barely (D). 0 need more VRAM than it has.
Can the Apple M2 Max run MiniMax H3 FL2VA?
Yes, in FP16 (rating C, usable).
Can the Apple M2 Max run MiniMax H3 Ref2VA?
Yes, in FP16 (rating C, usable).
Can the Apple M2 Max run Qwen-Image 2.1?
Yes, in FP16 (rating C, usable).
Can the Apple M2 Max run Z-Image Turbo?
Yes, in FP16 (rating C, usable).