text model · GLM · Android
Can I run GLM-4-9B-0414 on Samsung Galaxy S25 Ultra (16GB, 1TB config only)?
Yes. GLM-4-9B-0414 runs on Samsung Galaxy S25 Ultra (16GB, 1TB config only) at Q4_K_M (~7.2 GB of ~12 GB usable).
Runs at Q4_K_M using ~7.2 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. Samsung Galaxy S25 Ultra (16GB, 1TB config only) leaves ~4.8 GB of headroom, room to step up to Q8_0 for higher quality.
- Q4_K_M needed
- ~7.2 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~8 W
- Electricity / 1M tokens
- ~$0.05
- Pays for itself after
- ~3,598M tok
At ~$0.15/kWh and the estimated ~7 tok/s, a million generated tokens costs about $0.05 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$1,619 Samsung Galaxy S25 Ultra (16GB, 1TB config only) pays for itself after roughly 3,598 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
- 9B
- Q4_K_M size
- 5.74 GB
- Q8_0 size
- 9.31 GB
- Context
- 32k
- Memory
- 16 GB ram
- Usable for weights
- ~12 GB
- Power draw
- ~8 W
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
You could also run
Run GLM-4-9B-0414 on other hardware
FAQ
Can Samsung Galaxy S25 Ultra (16GB, 1TB config only) run GLM-4-9B-0414?
Yes. GLM-4-9B-0414 runs on Samsung Galaxy S25 Ultra (16GB, 1TB config only) at Q4_K_M (~7.2 GB of ~12 GB usable).
How much memory does GLM-4-9B-0414 need?
Samsung Galaxy S25 Ultra (16GB, 1TB config only) has room to spare. At Q4_K_M the weights are ~5.74 GB; with KV cache and runtime overhead, budget ~7.2 GB at a 4k context.
What is the best tool to run GLM-4-9B-0414 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/glm-4-9b-0414/samsung-s25-ultra-16gb) Sources
- gadgetversus.com
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- github.com/zai-org
- gsmarena.com/samsung_galaxy_s25_ultra-12750.php
- gsmarena.com/samsung_galaxy_s25_ultra-13322.php
- huggingface.co/bartowski
- huggingface.co/THUDM
- huggingface.co/zai-org
- layla-network.ai
- sammyfans.com
- sammyguru.com
- samsung.com
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.