Apple's on-device model (iOS 27)
63tokens per second
Much faster than reading
First word in 1.3 s · a 300-word answer in about 8 s
iPhone 17 Pro Max
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.
Gemma 4 E2B
63tokens per second
Much faster than reading
First word in 0.6 s · a 300-word answer in about 7 s
Qwen3.5 2B
51tokens per second
Much faster than reading
First word in 1.2 s · a 300-word answer in about 9 s
Gemma 4 E4B
27tokens per second
Much faster than reading
First word in 2.1 s · a 300-word answer in about 17 s
Every model on the iPhone 17 Pro Max
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.
30-day results and labeled 90-day samples, through · 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 · Check model requirements for your device