Apple · A19 · Phone
Best AI Models for iPhone 17 (8 GB)
Runs 1B models well; dense 3–4B fits but is slow at 15 tok/s, and 8–9B only just fit in the 5 GB iOS gives one app.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 14.6 t/s | 14.6 tok/s | Q4_K_M · 3.4 GB | |
| 2 | MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 25.1 t/s | 25.1 tok/s | Q4_K_M · 2.5 GB | |
| 3 | Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB · 27.0 t/s | 27.0 tok/s | Q4_K_M · 1.9 GB | |
| 4 | LFM3 1.7BLiquid AI Q4_K_M · 2.1 GB · 33.2 t/s | 33.2 tok/s | Q4_K_M · 2.1 GB | |
| 5 | MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 37.3 t/s | 37.3 tok/s | Q4_K_M · 1.6 GB |
The iPhone 17 suits smaller models: it runs 1B models well. iOS lets one app use about 5 GB of the 8 GB, so 8–9B models barely fit. Prompt reading is its weak spot: a 4K-token prompt waits 25 s before the first word on Qwen3.5 4B. A19 chip, released 2025.
iPhone 17 strengths and weaknesses
Strengths
- Runs 1B models: Llama 3.2 1B Instruct at 58.2 tok/s in 2.3 GB
Weaknesses
- 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 5 GB usable here
- Little room for context: Qwen3.5 9B uses 4.9 of 5 GB usable, 0.1 GB left
- Slow prompt reading: A 32K-token prompt on Qwen3.5 4B waits 3.4 min for the first token
Memory for models
5 GB of 8 GB14B models need 11.9 GB at Q4, more than the 5 GB available.
How much memory iOS lets one app use decides what phone works for local AI, not the camera or the screen.
Phones run small models. Output speed follows memory bandwidth (68.2 GB/s); grey rows need more than the 5 GB iOS gives one app.
- 1BLlama 3.2 1B Instruct · Q4_K_M · 2.3 GB58.2tok/s
- 3–4BQwen3.5 4B · Q4_K_M · 3.4 GB14.6tok/s
- 10.2tok/s
- 14BQwen3 14B · not at 4-bitneeds 11.9 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
iPhone generations: memory one app can use
A17 Pro → A19 Pro- iPhone 15 ProA17 Pro · 20234.5 GBup to 4B
- iPhone 16 Pro MaxA18 Pro · 20244.5 GBup to 4B
- iPhone 17A19 · 20255 GBup to 4B
- iPhone 17 Pro MaxA19 Pro · 20257 GBup to 9B (tight)
Every phone here has 8 GB or more, but iOS caps one app well below that. The iPhone 17 Pro Max is the first to fit an 8–9B model.
All 645 models on the iPhone 17
Featured onlyBest quant that fits in 5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 795.7 t/s | 2K | S100, Runs great | ||
SmolLM3 3B ONNXChat | Q4_K_M | 3.3 GB | 21.2 t/s | 66K | B61, Decent | |
| BF16 | 4.3 GB | 11.5 t/s | 262K | C43, Usable | ||
Supra 50M BaseChat | Q4_K_M | 0.3 GB | 132.6 t/s | 1K | S95, Runs great | |
Qwen2.5 1.5B Quantized.w8a8ChatFunctions | Q4_K_M | 1.8 GB | 33.4 t/s | 33K | A72, Runs well | |
| Q4_K_M | 3.7 GB | 18.0 t/s | 8K | B58, Decent | ||
| Q4_K_M | 0.1 GB | 367.2 t/s | 2K | S100, Runs great | ||
| Q4_K_M | 1.7 GB | 31.8 t/s | 4K | A71, Runs well | ||
Dots.ocrVision | Q4_K_M | 2.6 GB | 21.9 t/s | 131K | B62, Decent | |
| Q4_K_M | 0.3 GB | 159.1 t/s | 1K | S97, Runs great | ||
Bloom 560MChat | Q4_K_M | 1.6 GB | 129.0 t/s | — | S95, Runs great | |
BitCPM CANN 8BChat | Q3_K_M | 4.7 GB | 11.2 t/s | 33K | D27, Barely runs | |
| IQ4_XS | 5.0 GB | 27.3 t/s | 4K | C38, Usable | ||
Bloomz 560MChat | Q4_K_M | 0.4 GB | 129.0 t/s | 2K | S95, Runs great | |
| Q4_K_M | 4.2 GB | 16.5 t/s | 41K | B51, Decent |
Specs
- Chip
- A19
- CPU cores
- 6
- GPU cores
- 5
- Unified memory
- 8 GB LPDDR5X-8533
- For models
- 5 GB (iOS keeps 3 GB)
- Memory bandwidth
- 68.2 GB/s
- FP16 (dense)
- 7.5 TFLOPS
- NPU
- 16-core Neural Engine
- Released
- 2025-09-19
iPhone 17 FAQ
Can the iPhone 17 run an LLM offline?
Yes, small ones. Qwen3.5 4B runs at about 14.6 tok/s, and 1B models run around 58 tok/s. iOS lets one app use about 5 GB of the 8 GB, so larger models don't fit.
How much memory is available for AI on the iPhone 17?
About 5 GB of the 8 GB. iOS keeps roughly 3 GB for itself and other apps.
What is the largest model the iPhone 17 can run?
Qwen3.5 4B (4.7B) is the largest at 4-bit or better: at Q4_K_M it uses 3.4 GB, 69% of the available memory, and runs at about 14.6 tok/s.
How long does the iPhone 17 take to read a long prompt?
On Qwen3.5 4B, about 25 s for a 4K-token prompt and 3.4 min for a 32K-token document before the first word appears.