Qwen2.5 1.5B Instruct: every phone chip's best verified run.
| # | Device | SoC | Model | Backend | Prefill t/s | Decode t/s | RAM | App | Tested |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Apple iPhone18,2 | Apple A19 Pro | qwen2.5-1.5b-instruct-q4_k_m.gguf | llama.cpp · Q4_K_M | - | 64.4 | 11 GB | 16.163 (1830) | 6 weeks ago |
| 2 | Apple iPhone16,2 | Apple A17 Pro | Qwen2.5-1.5B-Instruct-Q4_K_M | gguf · Q4_K_M | 312.5 | 48.3 | 8 GB | 0.1.0 | 8 weeks ago |
← full leaderboard · API: /v1/board · tokforge.ai
