raven
Every model run on this chip under the standard preset, measured on 1 device. Two phones with the same chip differ in thermals, memory and clocks, so each keeps its own row rather than sharing a median.
| Device | Chip | Model | Quant | Runtime | Ctx | TTFT | Decode | Peak RAM | Source |
|---|---|---|---|---|---|---|---|---|---|
| Google Pixel 6 Pro | raven | LFM2.5 2.6B (Q4_0 ARM) | Q4_0 | gguf/cpu | 4096 | 11.15s | 11.7 t/s | 3.6 GB | community |
| Google Pixel 6 Pro | raven | MiniCPM5 1B (Q4) | Q4_K_M | gguf/cpu | 4096 | 0.70s | 25.4 t/sn=2 | 1.6 GB | community |
| Google Pixel 6 Pro | raven | SmolLM3 3B (Q4_0 ARM/GPU) | Q4_0 | gguf/cpu | 4096 | 3.86s | 8.3 t/s | 3.9 GB | community |
| Google Pixel 6 Pro | raven | Qwen3.5 2B (Q4_0 ARM) | Q4_0 | gguf/cpu | 4096 | 6.93s | 12.7 t/s | 2.7 GB | community |
| Google Pixel 6 Pro | raven | Gemma 4 E2B (Q4) | INT4 | litert/cpu | 4096 | 0.79s | 27.8 t/s | 2.9 GB | community |