text model · Mistral · iOS
Can I run Mistral Small 3 24B on iPhone 17?
No. Mistral Small 3 24B needs ~16.3 GB even at Q4_K_M, but iPhone 17 only has ~4.5 GB usable.
Needs ~16.3 GB even at Q4_K_M, but only ~4.5 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 11.8 GB: Mistral Small 3 24B needs roughly 16.3 GB at Q4_K_M and iPhone 17 leaves only about 4.5 GB usable for a model. The lightest tracked hardware that runs Mistral Small 3 24B is the Nvidia GeForce RTX 4090 (24GB) at 24 GB. See Mistral Small 3 24B on Nvidia GeForce RTX 4090 (24GB).
- Q4_K_M needed
- ~16.3 GB
- Usable on device
- ~4.5 GB
- Device memory
- 8 GB
Which quant fits
How to run it
On iOS use Apple Foundation Models (Built into iOS 26, ~3B on-device model, zero download, fully private.).
- Parameters
- 24B
- Q4_K_M size
- 14.33 GB
- Q8_0 size
- 25.05 GB
- Context
- 128k
- Ollama tag
- mistral-small3.2:24b
- Memory
- 8 GB unified
- Usable for weights
- ~4.5 GB
- Best runtime
- llama.cpp + Metal (via PocketPal or Off Grid app)
What you can run instead
Run Mistral Small 3 24B on other hardware
FAQ
Can iPhone 17 run Mistral Small 3 24B?
No. Mistral Small 3 24B needs ~16.3 GB even at Q4_K_M, but iPhone 17 only has ~4.5 GB usable.
How much memory does Mistral Small 3 24B need?
iPhone 17 does not have enough memory. At Q4_K_M the weights are ~14.33 GB; with KV cache and runtime overhead, budget ~16.3 GB at a 4k context.
What is the best tool to run Mistral Small 3 24B on iOS?
On iPhone and iPad, Apple Foundation Models (Built into iOS 26, ~3B on-device model, zero download, fully private.) is the standard choice. Phones realistically run 1B-4B class models. Anything larger thermally throttles or OOMs.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/mistral-small-3-24b/iphone-17) Sources
- apple.com
- developer.apple.com
- docs.mistral.ai
- en.wikipedia.org/wiki/Apple_A19
- en.wikipedia.org/wiki/IPhone_17
- enclaveai.app
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mainframecomputer
- huggingface.co
- layla-network.ai
- lmarena.ai
- macrumors.com
- ollama.com/library/mistral-small3.2
- ollama.com/library/mistral-small3.2/tags
- privatellm.app
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.