Qwen2.5 0.5B
on Unknown GPU · llama.cpp
Use cases
agentictool-use
Summary
User reports Qwen2.5-0.5B-Instruct at ~11.01 tok/s on a Samsung Galaxy A50s (Exynos 9611) phone, CPU only.
Setup is llama.cpp in Termux with Q4_K_M GGUF, ARM64 NEON, 4 threads; model uses ~542 MB RSS and ~463 MB on disk, TTFT ~2858 ms.
The run drives an offline Android AI Bridge workflow via llama-server on localhost:8080.