Apple · M4 · Tablet
Best AI Models for iPad Pro M4 13" (16 GB)
Runs 9B models at 13 tok/s; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 13.2 t/s | 13.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 25.8 t/s | 25.8 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 29.6 t/s | 29.6 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Q4_K_M · 7.9 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 7.9 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 62.8 t/s | 62.8 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Coding Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 7.9 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 7.9 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 25.8 t/s | 25.8 tok/s | overall | Q4_K_M · 3.4 GB |
| 3 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 15.2 t/s | 15.2 tok/s | overall | Q4_K_M · 7.6 GB |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 62.8 t/s | 62.8 tok/s | Q4_K_M · 5.5 GB | |
| 5 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 5.6 GB |
| # | Model | Speed | Reasoning Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3 8BAlibabaHow to run → Q4_K_M · 7.6 GB · 15.2 t/s | 15.2 tok/s | Q4_K_M · 7.6 GB | |
| 2 | Q4_K_M · 7.9 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 7.9 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 29.6 t/s | 29.6 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 16.8 t/s | 16.8 tok/s | Q4_K_M · 5.8 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 62.8 t/s | 62.8 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 25.8 t/s | 25.8 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Q4_K_M · 7.9 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 7.9 GB | |
| 3 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 62.8 t/s | 62.8 tok/s | Q4_K_M · 5.5 GB | |
| 4 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 5.6 GB | |
| 5 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 3.5 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 25.8 t/s | 25.8 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 62.8 t/s | 62.8 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 3.5 GB | |
| 4 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 15.8 t/s | 15.8 tok/s | Q4_K_M · 5.6 GB | |
| 5 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 15.2 t/s | 15.2 tok/s | Q4_K_M · 7.6 GB |
| # | Model | Speed | Vision Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 25.8 t/s | 25.8 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 29.6 t/s | 29.6 tok/s | Q4_K_M · 5.0 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 13.2 t/s | 13.2 tok/s | Q4_K_M · 6.6 GB | |
| 4 | MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 65.6 t/s | 65.6 tok/s | Q4_K_M · 1.6 GB | |
| 5 | LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 49.4 t/s | 49.4 tok/s | Q4_K_M · 2.4 GB |
The iPad Pro M4 13" is a mid-range 16 GB tablet: it runs 9B models at 13 tok/s. Among 16 GB machines, only the M1 Pro, M2 Pro and M5 write faster. iPadOS keeps about 3.5 GB, leaving 12.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 46 s before the first word on Qwen3.5 9B. M4 generation, released 2024; the newer M5 writes 27% faster with 1.9× the compute.
iPad Pro M4 13" strengths and weaknesses
Weaknesses
- 27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12.5 GB usable here
- Little room for context: Qwen3 14B uses 11.9 of 12.5 GB usable, 0.6 GB left
- Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 6.1 min for the first token
- No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX
Memory for models
12.5 GB of 16 GB27–31B models need 17.9 GB at Q4, more than the 12.5 GB available.Or rent an RTX 3090 (24 GB) from $0.20/hr →
Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
Output speed depends on memory bandwidth (120 GB/s). Grey rows need more than the 12.5 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB13.2tok/s
- 8.8tok/s
- 27–31BQwen3.8 27B · not at 4-bitneeds 17.9 GB
- 35B MoEQwen3.6 35B A3B · not at 4-bitneeds 22.0 GB
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
Chip generations: writing vs compute
M1 → M5Writing speed follows memory bandwidth and barely moved: 7.5 to 16.8 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.5 9B, same 16 GB.
All 971 models on the iPad Pro M4 13"
Featured onlyBest quant that fits in 12.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
WeVisOne VL 4BVisionFunctions | Q4_K_M | 4.7 GB | 24.8 t/s | 262K | A65, Runs well | |
| BF16 | 0.4 GB | 195.3 t/s | 1K | S100, Runs great | ||
Qwen3.5 0.8BVisionFunctions | Q4_K_M | 0.9 GB | 96.6 t/s | 262K | S90, Runs great | |
Sevclassifier Jev Style 1.5BChatFunctions | Q4_K_M | 1.7 GB | 65.6 t/s | 33K | S85, Runs great | |
Kimi K3 DSparkChat | Q4_K_M | 2.2 GB | 48.8 t/s | 1049K | A79, Runs well | |
| Q4_K_M | 0.5 GB | 280.0 t/s | 131K | S100, Runs great | ||
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16ChatFunctions | IQ2_M | 11.0 GB | 49.4 t/s | 262K | A69, Runs well | |
AesCode 8BVisionCodeFunctions | Q4_K_M | 8.0 GB | 14.3 t/s | 262K | B54, Decent | |
SenseNova Loop 9B PreviewVisionChatFunctions | Q4_K_M | 8.2 GB | 13.2 t/s | 262K | B52, Decent | |
Llm Jp 4.1 8B ThinkingChatFunctions | Q4_K_M | 7.6 GB | 14.7 t/s | 66K | B54, Decent | |
Apertus V1.5 8BVision | Q4_K_M | 8.5 GB | 14.3 t/s | — | B54, Decent | |
Molmo2 8BVision | Q4_K_M | 7.9 GB | 14.5 t/s | 37K | B54, Decent | |
LFM2.5 230MChatFunctions | Q4_K_M | 0.6 GB | 168.0 t/s | 128K | S98, Runs great | |
| Q4_K_M | 0.3 GB | 233.3 t/s | 1K | S100, Runs great | ||
Distil Lfm25 ShellperChatFunctions | Q4_K_M | 0.8 GB | 144.8 t/s | 128K | S96, Runs great |
Specs
- Chip
- M4
- CPU cores
- 10
- GPU cores
- 10
- Unified memory
- 16 GB
- For models
- 12.5 GB (iPadOS keeps 3.5 GB)
- Memory bandwidth
- 120 GB/s
- FP16 (dense)
- 8.6 TFLOPS
- Neural Engine
- 38 TOPS
- Released
- 2024-05-15
iPad Pro M4 13" FAQ
How much memory is available for AI on the iPad Pro M4 13" (16 GB)?
About 12.5 GB of the 16 GB. iPadOS keeps roughly 3.5 GB for itself and other apps.
What is the largest model the iPad Pro M4 13" (16 GB) can run?
GPT OSS 20B (20.9B) is the largest at 4-bit or better: at Q4_K_S it uses 12.4 GB, 99% of the available memory, and runs at about 29.6 tok/s.
Can the iPad Pro M4 13" (16 GB) run Qwen3.5 9B?
Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of the 12.5 GB available, and it is the best model that runs well on this machine.
Can the iPad Pro M4 13" (16 GB) run 27–31B models?
No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12.5 GB available.
How long does the iPad Pro M4 13" (16 GB) take to read a long prompt?
On Qwen3.5 9B, about 46 s for a 4K-token prompt and 6.1 min for a 32K-token document before the first word appears.