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 48.0 GB configuration
| Maker | Apple |
|---|---|
| Type | Desktop |
| Chip | Apple M4 Max (48 GB) · 16-core CPU, 40-core GPU |
| Unified memory | 48.0 GB |
| Usable for AI models | 36.0 GB |
| Memory bandwidth | 546 GB/s |
| FP16 compute | 18.4 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| Notes | M4 Max 14/32 = 410 GB/s; 512GB M3 Ultra option withdrawn Mar 2026 The 512 GB M3 Ultra option was withdrawn in March 2026.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) 48.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 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. | Gemma 4 26B-A4B | Q6_K | 25.0 GB | 76.3 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. | Qwen3.6 35B-A3B | Q5_K_M | 29.2 GB | 102 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. | MiniCPM-V 4.7 35B-A3B | Q5_K_M | 28.6 GB | 102 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. | Qwen3.5 35B-A3B | Q5_K_M | 29.2 GB | 102 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. | Nex N2 Mini (35B-A3B) | Q5_K_M | 28.6 GB | 102 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q5_K_M | 28.3 GB | 102 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q5_K_M | 29.2 GB | 102 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q5_K_M | 29.2 GB | 102 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q6_K | 29.5 GB | 90.1 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q6_K | 27.1 GB | 69.7 tok/s | Runs great |
Best Image models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 48.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 19.9 GB | 9.5 s | Runs great |
| 84Great quality (A) · 84 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. | Z-Image Turbo | FP16 | 22.7 GB | 15 s | Runs well |
| 85Excellent quality (A+) · 85 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. | ERNIE-Image Turbo | FP16 | 26.4 GB | 19 s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 20.2 GB | 23 s | Runs well |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 33 s | Runs well |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 5.9 s | Runs great |
Best Video models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 48.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 5.3 min | Runs well |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 26.0 GB | 63.3 min | Very slow |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q4 GGUF | 26.8 GB | 11.2 min | Runs wellencoder unloaded after use |
| 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP8 | 29.8 GB | 1.8 h | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 24.6 GB | 46.6 min | Very slow |
Best Decision models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 48.0 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 | 4.9 GB | 35 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 | 4.9 GB | 35 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 | 9.8 GB | 97 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 | 6.6 GB | 84 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q8_0 | 8.4 GB | 121 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 8.0 GB | 198 ms | Runs well |
| 80Great quality (A) · 80 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. | FRIDA-Decisions | F16 | 2.4 GB | 27 ms | Runs great |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | F16 | 1.7 GB | 18 ms | Runs great |
Other products with the Apple M4 Max (48 GB)
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.