text model · Mistral · Android
Can I run Devstral 2 123B on Samsung Galaxy S26 Ultra (16GB, 1TB config)?
No. Devstral 2 123B needs ~73.3 GB even at Q4_K_M, but Samsung Galaxy S26 Ultra (16GB, 1TB config) only has ~12 GB usable.
Needs ~73.3 GB even at Q4_K_M, but only ~12 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 61.3 GB: Devstral 2 123B needs roughly 73.3 GB at Q4_K_M and Samsung Galaxy S26 Ultra (16GB, 1TB config) leaves only about 12 GB usable for a model. The lightest tracked hardware that runs Devstral 2 123B is the Apple M4 Max (128GB) at 128 GB. See Devstral 2 123B on Apple M4 Max (128GB).
- Q4_K_M needed
- ~73.3 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 123B
- Q4_K_M size
- 69.75 GB
- Q8_0 size
- 123.73 GB
- Context
- 256k
- Ollama tag
- devstral-2:123b
- Memory
- 16 GB ram
- Usable for weights
- ~12 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
What you can run instead
Run Devstral 2 123B on other hardware
FAQ
Can Samsung Galaxy S26 Ultra (16GB, 1TB config) run Devstral 2 123B?
No. Devstral 2 123B needs ~73.3 GB even at Q4_K_M, but Samsung Galaxy S26 Ultra (16GB, 1TB config) only has ~12 GB usable.
How much memory does Devstral 2 123B need?
Samsung Galaxy S26 Ultra (16GB, 1TB config) does not have enough memory. At Q4_K_M the weights are ~69.75 GB; with KV cache and runtime overhead, budget ~73.3 GB at a 4k context.
What is the best tool to run Devstral 2 123B on Android?
On Android, PocketPal AI (Polished app, download GGUF and run offline.) is the go-to option. NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/devstral-2-123b/samsung-s26-ultra) 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.