text model · Qwen2.5 · Android
Can I run Qwen2.5 1.5B on Samsung Galaxy S24 Ultra?
Yes. Qwen2.5 1.5B runs on Samsung Galaxy S24 Ultra at Q4_K_M (~2.2 GB of ~8.5 GB usable).
Runs at Q4_K_M using ~2.2 GB of ~8.5 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Samsung Galaxy S24 Ultra leaves ~6.3 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~2.2 GB
- Usable on device
- ~8.5 GB
- Device memory
- 12 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~8 W
- Electricity / 1M tokens
- ~$0.01
- Pays for itself after
- ~2,651M tok
At ~$0.15/kWh and the estimated ~34 tok/s, a million generated tokens costs about $0.01 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$1,299 Samsung Galaxy S24 Ultra pays for itself after roughly 2,651 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 1.54B
- Q4_K_M size
- 1.12 GB
- Q8_0 size
- 1.89 GB
- Context
- 128k
- Ollama tag
- qwen2.5:1.5b
- Memory
- 12 GB ram
- Usable for weights
- ~8.5 GB
- Power draw
- ~8 W
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
You could also run
Run Qwen2.5 1.5B on other hardware
FAQ
Can Samsung Galaxy S24 Ultra run Qwen2.5 1.5B?
Yes. Qwen2.5 1.5B runs on Samsung Galaxy S24 Ultra at Q4_K_M (~2.2 GB of ~8.5 GB usable).
How much memory does Qwen2.5 1.5B need?
Samsung Galaxy S24 Ultra has room to spare. At Q4_K_M the weights are ~1.12 GB; with KV cache and runtime overhead, budget ~2.2 GB at a 4k context.
What is the best tool to run Qwen2.5 1.5B 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/qwen2.5-1.5b/samsung-s24-ultra) Sources
- androidauthority.com
- comparigon.com
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- gsmarena.com/samsung_galaxy_s24_ultra-12419.php
- gsmarena.com/samsung_galaxy_s24_ultra-12771.php
- gsmarena.com/samsung_galaxy_s24_ultra-review-2754p5.php
- huggingface.co/bartowski
- huggingface.co/Qwen
- layla-network.ai
- ollama.com
- qwenlm.github.io
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.