Hardware · Apple Silicon
What AI models can the Apple A18 Pro (8 GB) run?
- Unified memory
- 8.0 GB
- Usable for models
- 5.4 GB
- Memory bandwidth
- 60 GB/s
- FP16 compute
- 2.2 TFLOPS
- Released
- 2026
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 8.0 GB.
More about this hardware
| Maker | Apple Silicon |
|---|---|
| Type | Apple silicon (system on a chip) |
| Chip | Apple A18 Pro |
Apps that run models well on the Apple A18 Pro (8 GB)
1 product with the Apple A18 Pro (8 GB)
Best LLMs for the Apple A18 Pro (8 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q4_K_M | 4.2 GB | 27.6 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q4_K_M | 3.9 GB | 15.9 tok/s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q4_K_M | 3.8 GB | 15.4 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q4_K_M | 5.0 GB | 15.2 tok/s | Runs welltight fit |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q3_K_M | 5.1 GB | 52.4 tok/s | Runs welltight fit |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q3_K_M | 5.1 GB | 18.2 tok/s | Runs welltight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q4_K_M | 3.9 GB | 15.1 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q4_K_M | 4.1 GB | 13.6 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q4_K_M | 2.9 GB | 25.2 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q3_K_M | 5.1 GB | 18.2 tok/s | Runs welltight fit |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q6_K | 4.3 GB | 58.0 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 4.1 GB | 14.0 tok/s | Runs well |
Best Image models for the Apple A18 Pro (8 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 4.6 GB | 36 s | Runs welltight fit · encoder unloaded after use |
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 4.2 GB | 3.9 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q8 GGUF | 4.3 GB | 4.1 min | Very slowCPU offload |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 4.4 GB | 84 s | SlowCPU offload |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | SDXL-Lightning (4-step) | FP8 | 4.7 GB | 19 s | Runs welltight fit · encoder unloaded after use |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | Q4 GGUF | 4.3 GB | 81 s | SlowCPU offload |
Best Video models for the Apple A18 Pro (8 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 9.6 min | Runs welltight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 4.0 GB | 14.0 min | SlowCPU offload |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 4.7 GB | 33.7 min | Slowtight fit · CPU offload |
Best Decision models for the Apple A18 Pro (8 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 104 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 | 98 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 1.9 GB | 248 ms | Runs well |
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | F16 | 3.8 GB | 16 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 118 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | Q8_0 | 1.7 GB | 171 ms | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeBERTa v3 Large Zero-shot v2.0 | Q8_0 | 1.2 GB | 94 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 1.9 GB | 248 ms | Runs well |
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.