CodeGemma 2B on Apple iPhone 17 Pro / 17 Pro Max

Can the Apple iPhone 17 Pro / 17 Pro Max run CodeGemma 2B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 2.3 GB of 7.2 GB usable, with an estimated speed of 38.6 tok/s.

Best quant: Q4_K_M
Generation speed: 38.6 tok/s
Prompt processing: 767 tok/s
First token (1K prompt): 1.3 s
Largest safe context: 8K

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 CodeGemma 2B in the app

Want an agent? CodeGemma 2B 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 CodeGemma 2B

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 codegemma-2b-f16.gguf, the largest single file that fits (mobile apps can’t open a model split into parts).

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.
Sign in at huggingface.co (opens in a new tab) on the device and accept the model’s license, then download codegemma-2b-f16.gguf (opens in a new tab) on the device. It goes to Files › Downloads on an iPhone or iPad, or the Downloads folder on Android.
In PocketPal AI, tap the menu (☰), then Models, then + and Add Local Model, and pick the file.
Tap Load next to the model and start a chat. It runs on the device, offline.

Files and commands for a computer

Recommended for the Apple iPhone 17 Pro / 17 Pro Max: Q4_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 codegemma:2b-code-q4_K_M

Quantized files · GGUF

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

huggingface.co/google/codegemma-2b-GGUF (opens in a new tab)

ollama run hf.co/google/codegemma-2b-GGUF

Original weights · Hugging Face

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

huggingface.co/google/codegemma-2b (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Google approves it (usually within minutes to a few hours).

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_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 great: 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.	6.0 / 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.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	14.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.3 / 15
Match score	53.0 / 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`	1.8 GB	7.2 GB	63.4 tok/s	Runs great	9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	—
`Q3_K_M`	2.0 GB	7.2 GB	49.9 tok/s	Runs great	11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	—
`Q4_K_M`	2.3 GB	7.2 GB	38.6 tok/s	Runs great	13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	—
`Q5_K_M`	2.5 GB	7.2 GB	31.9 tok/s	Runs great	13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	—
`Q6_K`	2.8 GB	7.2 GB	26.8 tok/s	Runs well	13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	—
`Q8_0`	3.4 GB	7.2 GB	19.7 tok/s	Runs well	14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	—
`F16`	5.8 GB	7.2 GB	9.1 tok/s	Slow	14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	`F16`

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

Other hardware that runs it

14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 41.3 tok/s · Runs great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 57.8 tok/s · Runs great
14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 67.7 tok/s · Runs great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 63.2 tok/s · Runs great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 77.1 tok/s · Runs great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 84.4 tok/s · Runs great

Quick answers

How much memory does CodeGemma 2B need on the iPhone 17 Pro?

At Q4_K_M it needs about 2.3 GB. The iPhone 17 Pro has 7.2 GB usable.

How fast is CodeGemma 2B on the iPhone 17 Pro?

About 38.6 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of CodeGemma 2B should I use on the iPhone 17 Pro?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.