Hardware · Apple Silicon
What AI models can the Apple M3 Ultra (96 GB) run?
- Unified memory
- 96.0 GB
- Usable for models
- 72.0 GB
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Released
- 2025
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 96.0 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (two dies joined) |
| Chip | Apple M3 Ultra |
Apps that run models well on the Apple M3 Ultra (96 GB)
1 product with the Apple M3 Ultra (96 GB)
Best LLMs for the Apple M3 Ultra (96 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | F16 | 58.4 GB | 43.3 tok/s | Runs great |
| 93Excellent quality (A+) · 93 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. | Qwen3.6 35B-A3B | Q8_0 | 44.6 GB | 94.2 tok/s | Runs great |
| 93Excellent quality (A+) · 93 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. | Qwen3.5 35B-A3B | Q8_0 | 44.6 GB | 94.2 tok/s | Runs great |
| 93Excellent quality (A+) · 93 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. | MiniCPM-V 4.7 35B-A3B | Q8_0 | 43.9 GB | 94.2 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q8_0 | 48.8 GB | 106 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q8_0 | 43.7 GB | 94.2 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. | Nemotron 3.5 Bolt 74B-A9B | Q5_K_M | 59.6 GB | 62.2 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q8_0 | 44.6 GB | 94.2 tok/s | Runs great |
| 91Excellent quality (A+) · 91 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. | KAT-Coder V2.5 Dev (35B-A3B) | Q8_0 | 43.3 GB | 94.2 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | Ornith 1.5 35B-A3B | Q8_0 | 44.6 GB | 94.2 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | Kolibri 1 (78B-A3.5B) | Q6_K | 70.6 GB | 107 tok/s | Runs welltight fit |
| 89Excellent quality (A+) · 89 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. | Apodex 1.1 Mini (35B-A3B) | Q8_0 | 44.6 GB | 94.2 tok/s | Runs great |
Best Image models for the Apple M3 Ultra (96 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 89/100 (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 89/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 7.6 s | Runs great |
| 89Excellent quality (A+) · 89 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. | Qwen-Image 2.1 Turbo | FP16 | 46.7 GB | 49 s | Slow |
| 92Excellent quality (A+) · 92 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. | Ideogram 4 | FP16 | 57.3 GB | 1.8 min | Slow |
| 93Excellent quality (A+) · 93 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. | Qwen-Image 2.1 | FP16 | 57.0 GB | 4.2 min | Very slow |
| 84Great quality (A) · 84 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. | Z-Image Turbo | FP16 | 22.7 GB | 11 s | Runs great |
Best Video models for the Apple M3 Ultra (96 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 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. | LTX-2.5 (22B, video + audio) | FP8 | 48.3 GB | 5.8 min | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP8 | 44.3 GB | 25.4 min | Slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 50.8 min | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 1.9 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 1.9 h | Very slow |
Best Decision models for the Apple M3 Ultra (96 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 | 7.8 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 | 10.9 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 | 15.5 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 | 7.8 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 | 10.9 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 | 10.7 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 | 12.6 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 | 9.5 GB | 56 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.