Hardware · Apple Silicon
What AI models can the Apple M2 Ultra (192 GB) run?
- Unified memory
- 192 GB
- Usable for models
- 144 GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 27.2 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 192 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (two dies joined) |
| Chip | Apple M2 Ultra |
Apps that run models well on the Apple M2 Ultra (192 GB)
2 products with the Apple M2 Ultra (192 GB)
Best LLMs for the Apple M2 Ultra (192 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. | Nemotron 3.5 Super VL 120B-A12B | Q6_K | 114 GB | 41.6 tok/s | Runs great |
| 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. | Ornith 1.5 122B-A10B | Q6_K | 115 GB | 48.4 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. | Nemotron 3.5 Bolt 74B-A9B | Q8_0 | 91.6 GB | 40.5 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q4_K_M | 122 GB | 95.6 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. | Qwen3.5 122B-A10B | Q6_K | 115 GB | 48.4 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. | Kolibri 1 (78B-A3.5B) | Q8_0 | 95.1 GB | 84.4 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | F16 | 84.2 GB | 51.3 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | F16 | 84.2 GB | 51.3 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | F16 | 82.7 GB | 51.3 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | F16 | 91.9 GB | 58.9 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | F16 | 82.5 GB | 51.3 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | F16 | 84.2 GB | 51.3 tok/s | Runs great |
Best Image models for the Apple M2 Ultra (192 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 85/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | FP16 | 116 GB | 2.6 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 39 s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 7.9 s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 19 s | Runs well |
| 88Excellent quality (A+) · 88 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. | HunyuanImage 3.0 (80B-A13B) | FP8 | 86.9 GB | 3.9 min | Very slow |
| 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. | Z-Image Turbo | FP16 | 22.7 GB | 11 s | Runs great |
Best Video models for the Apple M2 Ultra (192 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 87/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 6.6 min | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP16 | 113 GB | 75.8 min | Very slow |
| 86Excellent quality (A+) · 86 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. | LTX-2.3 | FP16 | 75.4 GB | 29.1 min | Slow |
| 88Excellent quality (A+) · 88 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. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 3.6 h | Very slow |
| 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. | Cosmos3-Super Image2Video (64B) | FP16 | 139 GB | 2.7 h | Very slowtight fit |
Best Decision models for the Apple M2 Ultra (192 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 | 13.6 GB | 25 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 | 16.7 GB | 135 ms | Runs well |
| 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 | 21.3 GB | 96 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 | 13.6 GB | 25 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 | 16.7 GB | 135 ms | Runs well |
| 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 | 18.4 GB | 67 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 | 15.3 GB | 59 ms | Runs great |
| 86Excellent quality (A+) · 86 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. | Shieldstral 1.0 3B | Q8_0 | 16.4 GB | 130 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.