Hardware · Apple Silicon
What AI models can the Apple M3 Pro (36 GB) run?
- Unified memory
- 36.0 GB
- Usable for models
- 24.1 GB
- Memory bandwidth
- 150 GB/s
- FP16 compute
- 7.4 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 36.0 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (system on a chip) |
| Chip | Apple M3 Pro |
Apps that run models well on the Apple M3 Pro (36 GB)
2 products with the Apple M3 Pro (36 GB)
Best LLMs for the Apple M3 Pro (36 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q4_K_M | 18.7 GB | 36.6 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q4_K_M | 24.1 GB | 44.9 tok/s | Runs welltight fit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 23.8 GB | 44.9 tok/s | Runs welltight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q4_K_M | 22.0 GB | 44.9 tok/s | Runs welltight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q4_K_M | 20.2 GB | 32.8 tok/s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 35B-A3B | Q4_K_M | 24.1 GB | 44.9 tok/s | Runs welltight fit |
| 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen AgentWorld 35B-A3B | Q4_K_M | 23.8 GB | 44.9 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q3_K_M | 20.3 GB | 55.9 tok/s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy-Memory 30B-A3B | Q4_K_M | 21.7 GB | 44.9 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q3_K_M | 20.0 GB | 55.9 tok/s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q3_K_M | 20.3 GB | 55.9 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q3_K_M | 20.3 GB | 55.9 tok/s | Runs great |
Best Image models for the Apple M3 Pro (36 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 87/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 19.9 GB | 19 s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 20.2 GB | 45 s | Slow |
| 83Great quality (A) · 83 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. | ERNIE-Image Turbo | FP8 | 14.5 GB | 33 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 10 s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 12.6 GB | 26 s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP8 | 12.4 GB | 60 s | Slow |
Best Video models for the Apple M3 Pro (36 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 20.3 GB | 2.2 h | Very slowencoder unloaded after use |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP8 | 19.7 GB | 20.6 min | SlowCPU offload |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 S2V 14B (speech to video) | Q4 GGUF | 21.6 GB | 3.9 h | Very slowtight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 15.7 GB | 1.6 h | Very slowencoder unloaded after use |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 480P | Q4 GGUF | 20.6 GB | 3.5 h | Very slowtight fit |
Best Decision models for the Apple M3 Pro (36 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 | 4.0 GB | 87 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 | 4.0 GB | 87 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 | 61 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 | 38 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 | 4.0 GB | 87 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 43 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 3.5 GB | 72 ms | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass ModernBERT Large v3 | F16 | 1.5 GB | 32 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.