text model · LFM · iOS
Can I run LFM2.5 8B-A1B on iPad Pro M4 (16GB, 1TB/2TB config)?
Yes. LFM2.5 8B-A1B runs on iPad Pro M4 (16GB, 1TB/2TB config) at Q4_K_M (~6.7 GB of ~12 GB usable).
Runs at Q4_K_M using ~6.7 GB of ~12 GB usable. You have room for Q8_0 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. iPad Pro M4 (16GB, 1TB/2TB config) leaves ~5.3 GB of headroom, room to step up to Q8_0 for higher quality.
- Q4_K_M needed
- ~6.7 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
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
- 8.3B (MoE, 1.5B active)
- Q4_K_M size
- 5.2 GB
- Q8_0 size
- 9 GB
- Context
- 128k
- Ollama tag
- lfm2.5:8b-a1b
- Memory
- 16 GB unified
- Usable for weights
- ~12 GB
- Power draw
- ~14 W
- Best runtime
- MLX (via Python or Swift; mlx-lm package)
You could also run
Run LFM2.5 8B-A1B on other hardware
FAQ
Can iPad Pro M4 (16GB, 1TB/2TB config) run LFM2.5 8B-A1B?
Yes. LFM2.5 8B-A1B runs on iPad Pro M4 (16GB, 1TB/2TB config) at Q4_K_M (~6.7 GB of ~12 GB usable).
How much memory does LFM2.5 8B-A1B need?
iPad Pro M4 (16GB, 1TB/2TB config) has room to spare. At Q4_K_M the weights are ~5.2 GB; with KV cache and runtime overhead, budget ~6.7 GB at a 4k context. It is a Mixture-of-Experts model (8.3B total / 1.5B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run LFM2.5 8B-A1B 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/lfm2.5-8b-a1b/ipad-pro-m4-16gb) Sources
-
apple.com · 2 sources
-
developer.apple.com · 1 source
-
enclaveai.app · 1 source
-
github.com · 3 sources
-
gsmarena.com · 1 source
-
huggingface.co · 2 sources
-
layla-network.ai · 1 source
-
ollama.com · 1 source
-
phonearena.com · 1 source
-
privatellm.app · 1 source
-
support.apple.com · 2 sources
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.