Products · Apple · Desktop
Apple Mac Studio (2025) (M4 Max or M3 Ultra)
- Chips
- Apple M4 Max or Apple M3 Ultra
- Unified memory
- 36, 48, 64, 96, 128, 256 or 512 GB
- Launch price
- $1,999–$9,499
- Released
- 2025
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 M4 Max · 14-core CPU, 32-core GPU | 36.0 GB | 24.1 GB | 410 GB/s | 462 of 622 | $1,999 |
| Apple M4 Max · 16-core CPU, 40-core GPU | 48.0 GB | 36.0 GB | 546 GB/s | 491 of 622 | $2,499 |
| Apple M4 Max · 16-core CPU, 40-core GPU | 64.0 GB | 48.0 GB | 546 GB/s | 504 of 622 | — |
| Apple M3 Ultra · 28-core CPU, 60-core GPU | 96.0 GB | 72.0 GB | 819 GB/s | 525 of 622 | $3,999 |
| Apple M3 Ultra · 32-core CPU, 80-core GPU | 96.0 GB | 72.0 GB | 819 GB/s | 525 of 622 | $5,499 |
| Apple M4 Max · 16-core CPU, 40-core GPU | 128 GB | 96.0 GB | 546 GB/s | 533 of 622 | — |
| Apple M3 Ultra · 28-core CPU, 60-core GPU | 256 GB | 192 GB | 819 GB/s | 576 of 622 | — |
| Apple M3 Ultra · 32-core CPU, 80-core GPU | 256 GB | 192 GB | 819 GB/s | 576 of 622 | — |
| Apple M3 Ultra · 32-core CPU, 80-core GPU | 512 GB | 384 GB | 819 GB/s | 600 of 622 | $9,499 |
Specifications 512 GB configuration
| Maker | Apple |
|---|---|
| Type | Desktop |
| Chip | Apple M3 Ultra (512 GB) · 32-core CPU, 80-core GPU |
| Unified memory | 512 GB |
| Usable for AI models | 384 GB |
| Memory bandwidth | 819 GB/s |
| FP16 compute | 28.4 TFLOPS |
| Notes | M4 Max 14/32 = 410 GB/s; 512GB M3 Ultra option withdrawn Mar 2026 The 512 GB M3 Ultra option was withdrawn in March 2026. |
| Product page | support.apple.com (opens in a new tab) |
Best LLMs for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 512 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | MiMo V2.6 Flash (310B-A15B) | Q5_K_M | 252 GB | 40.9 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (284B-A13B) | Q6_K | 281 GB | 39.6 tok/s | Runs great |
| 96Excellent quality (A+) · 96 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. | Qwen3.8 Flash Next (125B-A6B) | Q8_0 | 222 GB | 57.4 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Inkling Small (276B-A12B) | Q6_K | 250 GB | 42.4 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Naive N0.5 Flash (309B-A15.5B) | Q5_K_M | 251 GB | 39.7 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.5 (310B-A15B) | Q5_K_M | 252 GB | 40.9 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Intern-S2 (397B-A17B) | Q5_K_M | 318 GB | 36.7 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Nex N2 Pro (397B-A17B) | Q5_K_M | 313 GB | 36.7 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (April 2026) | Q6_K | 270 GB | 39.6 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Qwen3.5 397B-A17B | Q5_K_M | 318 GB | 36.7 tok/s | Runs great |
Best Image models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 512 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 7.6 s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 18 s | Runs well |
| 84Great quality (A) · 84 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. | Z-Image Turbo | FP16 | 22.7 GB | 11 s | Runs great |
| 90Excellent quality (A+) · 90 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. | HunyuanImage 3.0 (80B-A13B) | FP16 | 170 GB | 4.2 min | Very slow |
| 92Excellent quality (A+) · 92 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. | Cosmos3-Super Text2Image (64B) | FP16 | 133 GB | 2.8 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 38 s | Runs well |
Best Video models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 512 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 79/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 6.4 min | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP16 | 113 GB | 73.3 min | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Image2Video (64B) | FP16 | 139 GB | 2.6 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 28.2 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 3.5 h | Very slow |
Best Decision models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 512 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 v3.5 | F16 | 32.8 GB | 24 ms | Runs great |
| 90Excellent quality (A+) · 90 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. | Qwen3 Reranker 4B | Q8_0 | 35.9 GB | 130 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 4B | F16 | 40.5 GB | 92 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 v3 | F16 | 32.8 GB | 24 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 35.9 GB | 130 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 35.6 GB | 125 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 3B | F16 | 37.6 GB | 65 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 v2 | F16 | 34.5 GB | 56 ms | Runs great |
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.