Apple Mac Studio (M5 Max or M5 Ultra)

Hardware · Apple Silicon

What AI models can the Apple M5 Ultra (256 GB) run?

Unified memory
256 GB
Usable for models
192 GB
Memory bandwidth
1,200 GB/s
FP16 compute
37.7 TFLOPS
Released
2026

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 256 GB.

More about this hardware

MakerApple Silicon
TypeApple silicon (two dies joined)
ChipApple M5 Ultra

Apps that run models well on the Apple M5 Ultra (256 GB)

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

1 product with the Apple M5 Ultra (256 GB)

Best LLMs for the Apple M5 Ultra (256 GB)

Quality Model Quant Memory Speed Runs
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Super VL 120B-A12BNVIDIA Q8_0 148 GB 44.7 tok/s Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B)Alibaba Q5_K_M 144 GB 108 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 122B-A10BDeepReinforce Q8_0 149 GB 51.8 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 122B-A10BAlibaba Q8_0 149 GB 51.8 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B)StepFun Q5_K_M 159 GB 71.4 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B)StepFun Q5_K_M 158 GB 71.4 tok/s Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B)MiniMax Q4_K_M 158 GB 88.9 tok/s Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3 Super 120B-A12BNVIDIA Q8_0 147 GB 44.7 tok/s Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B)MiniMax Q4_K_M 158 GB 88.9 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B)Thinking Machines Lab Q4_K_M 178 GB 78.0 tok/s Runs welltight fit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.1 (230B-A10B)MiniMax Q4_K_M 158 GB 88.9 tok/s Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 235B-A22B Thinking 2507Alibaba Q4_K_M 161 GB 48.3 tok/s Runs great

Best Image models for the Apple M5 Ultra (256 GB)

Quality Model Quant Memory Speed Runs
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. MiniMax H3 ImageMiniMax FP16 138 GB 34 s Runs well
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [dev]Black Forest Labs FP16 116 GB 2.1 min Slow
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP16 37.4 GB 15 s Runs well
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP16 37.1 GB 6.2 s Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP16 26.4 GB 11 s Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP16 22.7 GB 8.6 s Runs great

Best Video models for the Apple M5 Ultra (256 GB)

Quality Model Quant Memory Speed Runs
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks FP16 82.5 GB 5.2 min Runs well
90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. MiniMax H3 (33B, video + audio)MiniMax FP16 113 GB 59.3 min Very slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Cosmos3-Super Image2Video (64B)NVIDIA FP16 139 GB 2.1 h Very slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.3Lightricks FP16 75.4 GB 22.8 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Pro (29B, video + audio)Sber AI FP16 85.4 GB 2.8 h Very slow

Best Decision models for the Apple M5 Ultra (256 GB)

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 4BAlibaba Q8_0 20.5 GB 98 ms Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. zerank-2ZeroEntropy Q8_0 20.5 GB 98 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI F16 17.4 GB 19 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Shieldstral 1.0 3BMistral AI Q8_0 20.3 GB 94 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Intern-Decision 4BShanghai AI Lab F16 25.1 GB 69 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI F16 17.4 GB 19 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. d1 3BLiquid AI F16 22.2 GB 49 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-large v2Mixedbread F16 19.1 GB 43 ms Runs great

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?