gpt-oss 20B on Apple iPhone 17 Pro / 17 Pro Max

Can the Apple iPhone 17 Pro / 17 Pro Max run gpt-oss 20B?

No, it doesn’t fit (over the app memory limit)

No. gpt-oss 20B needs about 12.7 GB even at MXFP4; the Apple iPhone 17 Pro / 17 Pro Max has 7.2 GB usable.

Download gpt-oss 20B

Recommended: MXFP4. 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 gpt-oss:20b

Quantized files · GGUF

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

Download the MXFP4 file (opens in a new tab)

huggingface.co/ggml-org/gpt-oss-20b-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/gpt-oss-20b-GGUF:MXFP4

Original weights · Hugging Face

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

huggingface.co/openai/gpt-oss-20b (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/openai/gpt-oss (opens in a new tab)

git clone https://github.com/openai/gpt-oss

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at MXFP4, 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 Won't runover the app memory limit: 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.	9.5 / 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.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	9.5 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

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

Quant	Memory needed	Available	Speed	Runs	Quality	File to pick in the app
`MXFP4`	12.7 GB	7.2 GB	—	Won't runover the app memory limit	70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	`MXFP4`
`F16`	42.6 GB	7.2 GB	—	Won't runover the app memory limit	70Great quality (A) · 70 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.

Hardware that can run it

70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT MXFP4 · 120 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB MXFP4 · 77.6 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER MXFP4 · 134 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER MXFP4 · 141 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5060 Ti 16GB MXFP4 · 105 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti MXFP4 · 156 tok/s · Runs great

Models that do run on the Apple iPhone 17 Pro / 17 Pro Max

66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q4_K_M · 21.5 tok/s
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B) Q4_K_M · 59.6 tok/s
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q3_K_M · 43.1 tok/s
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q4_K_M · 23.2 tok/s
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E4B Q4_K_M · 21.5 tok/s

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.