Granite 4.2 8B on Apple iPhone 17 Pro / 17 Pro Max

Can the Apple iPhone 17 Pro / 17 Pro Max run Granite 4.2 8B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 6.2 GB of 7.2 GB usable, with an estimated speed of 14.3 tok/s.

Best quant: Q3_K_M
Generation speed: 14.3 tok/s
Prompt processing: 219 tok/s
First token (1K prompt): 4.7 s
Largest safe context: 13K

Best app to run it on the Apple iPhone 17 Pro / 17 Pro Max

On iOS

PocketPal AI

Mobile app · runs on llama.cpp

Runs the model on the device itself, offline: download it once in the app.

Get it on the App Store Then download Granite 4.2 8B in the app

Want an agent? Granite 4.2 8B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Granite 4.2 8B

On a phone, tablet or other mobile device you install a chat app and get the model file through it, so there are no commands to copy. Use granite-4.2-8b-Q3_K_M.gguf for the Apple iPhone 17 Pro / 17 Pro Max.

On iPhone or iPad

PocketPal AI

Free mobile app · runs the model on the device with llama.cpp

Get it on the App Store

Install PocketPal AI (free) and open it.
Tap the menu (☰), then Models, then + and Add from Hugging Face.
Search for ibm-granite/granite-4.2-8b-GGUF, open it and download granite-4.2-8b-Q3_K_M.gguf.
Tap Load next to the model and start a chat. It runs on the device, with no connection needed from then on.

Files and commands for a computer

Recommended for the Apple iPhone 17 Pro / 17 Pro Max: Q3_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run granite4.2:8b-q3_K_M

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q3_K_M file (opens in a new tab)

huggingface.co/ibm-granite/granite-4.2-8b-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-4.2-8b-GGUF:Q3_K_M

Original weights · Hugging Face

Full-precision files from IBM, for fine-tuning, vLLM, Transformers.

huggingface.co/ibm-granite/granite-4.2-8b (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from IBM. The weights themselves download from Hugging Face.

github.com/ibm-granite/granite-4.2-language-models (opens in a new tab)

git clone https://github.com/ibm-granite/granite-4.2-language-models

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs welltight fit: How well it runs on the Apple iPhone 17 Pro / 17 Pro Max: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	25.7 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	73.7 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple iPhone 17 Pro / 17 Pro Max

Quant	Memory needed	Available	Speed	Runs	Quality	File to pick in the app
`Q2_K`	5.5 GB	7.2 GB	18.1 tok/s	Runs well	47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	`Q2_K`
`Q3_K_M`	6.2 GB	7.2 GB	14.3 tok/s	Runs welltight fit	57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	`Q3_K_M`
`Q4_K_M`	7.3 GB	7.2 GB	—	Won't runover the app memory limit	64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	`Q4_K_M`
`Q5_K_M`	8.2 GB	7.2 GB	—	Won't runover the app memory limit	65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	`Q5_K_M`
`Q6_K`	9.1 GB	7.2 GB	—	Won't runover the app memory limit	67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	`Q6_K`
`Q8_0`	11.3 GB	7.2 GB	—	Won't runover the app memory limit	68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	`Q8_0`
`F16`	19.5 GB	7.2 GB	—	Won't runover the app memory limit	68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	`BF16`

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 47.8 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 52.3 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 63.7 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 68.2 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 58.7 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 39.2 tok/s · Runs great

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.