# iPhone 17 Pro Max > How fast Apple's on-device model (iOS 27), Gemma 4 E2B, Qwen3.5 2B and Gemma 4 E4B run on the iPhone 17 Pro Max (A19 Pro) in Loci: Gemma 4 E4B writes 27 tokens per second, first word in 2.1 s. Canonical: https://askloci.ai/speed/iphone-17-pro-max/ Last updated: 2026-11-06 Gemma 4 E4B writes 27 tokens per second on the iPhone 17 Pro Max, with the first word in 2.1 s. The fastest model here is Apple's on-device model (iOS 27), at 63. ### Apple's on-device model (iOS 27) **63 tokens per second** Much faster than reading First word in 1.3 s · a 300-word answer in about 8 s ### What 63 tokens per second looks like Sure. Start with the task you have been putting off, while your focus is fresh. Give it one uninterrupted hour, then take a short walk. Answer messages in one batch after lunch, and keep the last half hour to plan tomorrow, so the morning starts without decisions. Typical range 59–73 tokens per second · 11 iPhones [Apple's on-device model (iOS 27) on the iPhone 17 Pro Max](https://askloci.ai/speed/iphone-17-pro-max/apple-foundation-ios27/) ### Gemma 4 E2B **63 tokens per second** Much faster than reading First word in 0.6 s · a 300-word answer in about 7 s ### What 63 tokens per second looks like Sure. Start with the task you have been putting off, while your focus is fresh. Give it one uninterrupted hour, then take a short walk. Answer messages in one batch after lunch, and keep the last half hour to plan tomorrow, so the morning starts without decisions. Typical range 56–68 tokens per second · 27 iPhones [Gemma 4 E2B on the iPhone 17 Pro Max](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e2b/) ### Qwen3.5 2B **51 tokens per second** Much faster than reading First word in 1.2 s · a 300-word answer in about 9 s ### What 51 tokens per second looks like Sure. Start with the task you have been putting off, while your focus is fresh. Give it one uninterrupted hour, then take a short walk. Answer messages in one batch after lunch, and keep the last half hour to plan tomorrow, so the morning starts without decisions. Typical range 46–56 tokens per second · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-06 [Qwen3.5 2B on the iPhone 17 Pro Max](https://askloci.ai/speed/iphone-17-pro-max/qwen3-5-2b/) ### Gemma 4 E4B **27 tokens per second** Much faster than reading First word in 2.1 s · a 300-word answer in about 17 s ### What 27 tokens per second looks like Sure. Start with the task you have been putting off, while your focus is fresh. Give it one uninterrupted hour, then take a short walk. Answer messages in one batch after lunch, and keep the last half hour to plan tomorrow, so the morning starts without decisions. Typical range 26–29 tokens per second · 29 iPhones [Gemma 4 E4B on the iPhone 17 Pro Max](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e4b/) ## Every model on the iPhone 17 Pro Max - [Apple's on-device model (iOS 27)](https://askloci.ai/speed/iphone-17-pro-max/apple-foundation-ios27/) — 63 tok/s · First word 1.3 s · 11 iPhones - [Gemma 4 E2B](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e2b/) — 63 tok/s · First word 0.6 s · 27 iPhones - [Qwen3.5 2B](https://askloci.ai/speed/iphone-17-pro-max/qwen3-5-2b/) — 51 tok/s · First word 1.2 s · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-06 - [Gemma 4 E4B](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e4b/) — 27 tok/s · First word 2.1 s · 29 iPhones ## Questions ### What's the fastest AI model on the iPhone 17 Pro Max? Apple's on-device model (iOS 27), at 63 tokens per second, with the first word in 1.3 s, measured in Loci on 11 iPhones. ### Can the iPhone 17 Pro Max run Apple's on-device model (iOS 27)? Yes: Apple's on-device model (iOS 27) writes 63 tokens per second on the iPhone 17 Pro Max, much faster than reading, with the first word in 1.3 s. ### Can the iPhone 17 Pro Max run Gemma 4 E2B? Yes: Gemma 4 E2B writes 63 tokens per second on the iPhone 17 Pro Max, much faster than reading, with the first word in 0.6 s. ### Can the iPhone 17 Pro Max run Qwen3.5 2B? Yes: Qwen3.5 2B writes 51 tokens per second on the iPhone 17 Pro Max, much faster than reading, with the first word in 1.2 s. ### Can the iPhone 17 Pro Max run Gemma 4 E4B? Yes: Gemma 4 E4B writes 27 tokens per second on the iPhone 17 Pro Max, much faster than reading, with the first word in 2.1 s. ## Run Gemma 4 E4B on your iPhone Loci is free, needs no account, and keeps every conversation on your device. - [Download for iPhone](https://apps.apple.com/app/id6762100748) 30-day results and labeled 90-day samples, through November 6, 2026 · updated daily ## How these speeds are measured - Every number comes from real chats in Loci, timed on the device that wrote the answer, with Loci's default settings. - **Tokens per second** is how fast an answer is written once it starts. On phones, four characters of text count as one token for every model; on a Mac, Loci counts the model's own tokens. Reading pace is about 5. - **First word** is how long an answer takes to start after you send a message. Longer conversations take longer. - Each device counts once. The large number is the median; the typical range covers the middle half of devices. - Results use the last 30 days when enough devices have been measured. Otherwise, labeled 90-day samples include older measurements under the same sample and app-version requirements. - Each phone speed comes from at least 10 phones of that model. Different phone models and Android chip variants are measured separately. Open a result to see its sample size. - On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out. [Methods, fixed editions and citations](https://askloci.ai/speed/research/) [Check model requirements for your device](https://askloci.ai/can-my-device-run/)