Hardware · Apple Silicon
What AI models can the Apple M4 Max (48 GB) run?
- Unified memory
- 48.0 GB
- Usable for models
- 36.0 GB
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Released
- 2024
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 48.0 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (system on a chip) |
| Chip | Apple M4 Max |
Apps that run models well on the Apple M4 Max (48 GB)
3 products with the Apple M4 Max (48 GB)
Best LLMs for the Apple M4 Max (48 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 |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q5_K_M | 29.2 GB | 102 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q5_K_M | 29.2 GB | 102 tok/s | Runs great |
Best Image models for the Apple M4 Max (48 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 M4 Max (48 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 M4 Max (48 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 |
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.