Hardware · Apple Silicon
What AI models can the Apple M3 Max (64 GB) run?
- Unified memory
- 64.0 GB
- Usable for models
- 48.0 GB
- Memory bandwidth
- 400 GB/s
- FP16 compute
- 16.4 TFLOPS
- Released
- 2023
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 64.0 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (system on a chip) |
| Chip | Apple M3 Max |
Apps that run models well on the Apple M3 Max (64 GB)
2 products with the Apple M3 Max (64 GB)
Best LLMs for the Apple M3 Max (64 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | Qwen3.6 35B-A3B | Q6_K | 34.1 GB | 72.3 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. | Gemma 4 26B-A4B | Q8_0 | 32.2 GB | 46.6 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. | MiniCPM-V 4.7 35B-A3B | Q6_K | 33.5 GB | 72.3 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. | Qwen3.5 35B-A3B | Q6_K | 34.1 GB | 72.3 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. | Nex N2 Mini (35B-A3B) | Q6_K | 33.4 GB | 72.3 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | KAT-Coder V2.5 Dev (35B-A3B) | Q6_K | 33.0 GB | 72.3 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | Sage-A1.5 35B-A3B | Q6_K | 34.1 GB | 72.3 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Flint (40B-A2.5B) | Q6_K | 37.3 GB | 82.4 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Ornith 1.5 35B-A3B | Q6_K | 34.1 GB | 72.3 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | Apodex 1.1 Mini (35B-A3B) | Q6_K | 34.1 GB | 72.3 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | Ornith 1.0 35B-A3B | Q6_K | 34.1 GB | 72.3 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. | GLM-4.7 Flash (30B-A3B) | Q8_0 | 38.0 GB | 56.4 tok/s | Runs great |
Best Image models for the Apple M3 Max (64 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 27 s | Runs well |
| 85Excellent quality (A+) · 85 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. | ERNIE-Image Turbo | FP16 | 26.4 GB | 20 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 19.9 GB | 10 s | Runs great |
| 84Great quality (A) · 84 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. | Z-Image Turbo | FP16 | 22.7 GB | 16 s | Runs well |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP8 | 30.8 GB | 67 s | Slow |
| 91Excellent quality (A+) · 91 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 3 Image Klein | FP16 | 22.4 GB | 36 s | Runs well |
Best Video models for the Apple M3 Max (64 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q4 GGUF | 39.9 GB | 11.6 min | Runs well |
| 66Good quality (B) · 66 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. | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 5.7 min | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 3.3 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 3.3 h | Very slow |
| 84Great quality (A) · 84 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. | LTX-2.3 | FP8 | 44.3 GB | 38.3 min | Slowtight fit |
Best Decision models for the Apple M3 Max (64 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 | 5.9 GB | 40 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 | 5.9 GB | 40 ms | Runs great |
| 82Great quality (A) · 82 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. | d1 3B | Q8_0 | 7.8 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 | 7.6 GB | 97 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. | FRIDA-Decisions | F16 | 2.4 GB | 30 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 | 19 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. | Qwen3 Reranker 0.6B | F16 | 5.9 GB | 40 ms | Runs great |
| 80Great quality (A) · 80 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. | zerank-1 small | Q8_0 | 6.5 GB | 99 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.