Can LFM2.5 8B-A1B run on vivo X100 Pro?

YESRuns great
Grade S · 100/100 · formula estimate

What this means

Our estimate says LFM2.5 8B-A1B should fit comfortably on your vivo X100 Pro.

Download the Q4_K_M version, which is about 5.2 GB. We expect it to use about 6.6 GB of the roughly 12 GB available to a model on this phone.

At the estimated speed, a roughly 300-word answer may take about 8 seconds to finish.

This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.

53.2tokens/s
estimated · instant
6.6GB
needed at Q4_K_M
Q4_K_M
quant checked
S
grade · 100/100
needs 6.6 GBusable 12 GB
Dimensity 930016 GB RAMCPU / GPUalso sold with 12 GB

See how fast it feels

Estimated at 53.2 tokens/s — instant. A ~300-word reply takes about 8 seconds on this phone.

Live demo · 53.2 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (5.2 GB) + mmap overhead5.5
KV cache4K context window0.6
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context6.6
Usable on vivo X100 Pro16 GB RAM − Android system reserve12
Headroomleft for the OS and your other apps5.4

Pick your quant

QuantDownloadVerdictSpeed
Q4_0 4.8 GB Runs great~57.6 tokens/s
Q4_K_M BEST HERE5.2 GB Runs great~53.2 tokens/s
Q5_K_M 6 GB Runs great~46.1 tokens/s
Q6_K 7 GB Runs great~39.5 tokens/s
Q8_0 9 GB Runs great~30.7 tokens/s

Get it running in 3 steps

1
Install PocketPal from the Play Store — free, no account needed.
2
Download "LFM2.5 8B-A1B Q4_K_M" in the in-app model hub — 5.2 GB, use Wi-Fi. Search Hugging Face for LiquidAI/LFM2.5-8B-A1B-GGUF and pick the Q4_K_M file.
3
Set context to 4K — expect ~53.2 tokens/s on this phone.

Related checks

MORE ON VIVO X100 PRO
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
LFM2.5 8B-A1B ON OTHER PHONES
Galaxy S25 UltraGalaxy S25Galaxy S24 UltraGalaxy S24Galaxy S23 Ultra