Check my GPU

Products · · Desktop

Apple Mac Studio (2022) (M1 Max or M1 Ultra)

Chips
Apple M1 Max or Apple M1 Ultra
Unified memory
32, 64 or 128 GB
Launch price from
$1,999
Released
2022

View on the Apple website (opens in a new tab) Full AI report

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Configuration Memory Usable for AI Bandwidth LLMs that run well Launch price
Apple M1 Max · 10-core CPU, 24-core GPU 32.0 GB 21.4 GB 400 GB/s 401 of 536 $1,999
Apple M1 Max · 10-core CPU, 32-core GPU 32.0 GB 21.4 GB 400 GB/s 401 of 536 $2,199
Apple M1 Max · 10-core CPU, 24-core GPU 64.0 GB 48.0 GB 400 GB/s 439 of 536 $2,399
Apple M1 Max · 10-core CPU, 32-core GPU 64.0 GB 48.0 GB 400 GB/s 439 of 536 $2,599
Apple M1 Ultra · 20-core CPU, 48-core GPU 64.0 GB 48.0 GB 800 GB/s 439 of 536 $3,999
Apple M1 Ultra · 20-core CPU, 64-core GPU 64.0 GB 48.0 GB 800 GB/s 439 of 536 $4,999
Apple M1 Ultra · 20-core CPU, 48-core GPU 128 GB 96.0 GB 800 GB/s 465 of 536 $4,799
Apple M1 Ultra · 20-core CPU, 64-core GPU 128 GB 96.0 GB 800 GB/s 465 of 536 $5,799

Specifications 128 GB configuration

MakerApple
TypeDesktop
ChipApple M1 Ultra (128 GB) · 20-core CPU, 64-core GPU
Unified memory128 GB
Usable for AI models96.0 GB
Memory bandwidth800 GB/s
FP16 compute21.0 TFLOPS
Maker’s pagesupport.apple.com (opens in a new tab)

Best LLMs for the Apple Mac Studio (2022) (M1 Max or M1 Ultra) 128 GB

Grade · points Model Quant Memory Speed Fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 122B-A10BAlibaba Q4_K_M 84.8 GB 42.3 tok/s Tight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3 Coder Next (80B-A3B)Alibaba Q6_K 73.8 GB 97.8 tok/s Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3-Next 80B-A3B ThinkingAlibaba Q6_K 75.2 GB 97.8 tok/s Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 42.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 Qwen3.6 35B-A3BAlibaba Q8_0 46.6 GB 71.7 tok/s Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 Qwen3.5 35B-A3BAlibaba Q8_0 46.6 GB 71.7 tok/s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 gpt-oss 120BOpenAI MXFP4 75.2 GB 88.7 tok/s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3 Next 80B-A3B InstructAlibaba Q6_K 75.2 GB 97.8 tok/s Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 Ornith 1.5 35B-A3BDeepReinforce Q8_0 46.6 GB 71.7 tok/s Runs well
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Laguna S 2.1 (118B-A8B)Poolside Q5_K_M 93.4 GB 43.7 tok/s Tight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 Apodex 1.1 Mini (35B-A3B)Apodex Q8_0 46.6 GB 71.7 tok/s Runs well

Best Image models for the Apple Mac Studio (2022) (M1 Max or M1 Ultra) 128 GB

Grade · points Model Precision Memory Time per output Fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15 FLUX.2 [klein] 9BBlack Forest Labs FP16 37.1 GB 9.6 s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 40.6/45, Memory fit 25.0/25, Speed 3.6/15, Memory use 14.3/15 FLUX.2 [dev]Black Forest Labs FP8 59.7 GB 2.9 min Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 15.0/15 Qwen-Image 2512Alibaba FP16 63.8 GB 8.0 min Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 15.0/15 Qwen-ImageAlibaba FP16 63.8 GB 8.0 min Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 5.5/15 Z-Image TurboAlibaba (Tongyi) FP16 22.7 GB 13 s Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 5.0/15, Memory use 15.0/15 HiDream-I1 DevHiDream.ai FP16 64.4 GB 1.5 min Runs well

Best Video models for the Apple Mac Studio (2022) (M1 Max or M1 Ultra) 128 GB

Grade · points Model Precision Memory Time per output Fit
83 ptsGreat (A) · 83 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15 LTX-2.3Lightricks FP16 75.4 GB 35.4 min Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 15.0/15 LTX-2 (19B, video + audio)Lightricks FP16 75.4 GB 35.4 min Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 13.9/15 Wan 2.2 I2V A14BAlibaba FP16 58.0 GB 2.4 h Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 13.9/15 Wan 2.2 T2V A14BAlibaba FP16 58.0 GB 2.4 h Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 11.5/15 LTX-Video 13B 0.9.8 (distilled)Lightricks FP16 47.9 GB 5.3 min Runs well

Spec sources

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.