Prompt: (raw) (yaml)
words:27 bytes:174
| model | words | bytes | total duration |
load duration |
prompt eval count |
prompt eval duration |
prompt eval rate |
eval count |
eval duration |
eval rate |
|---|---|---|---|---|---|---|---|---|---|---|
| granite3.2-vision:2b | 183 | 1134 | 28.182379709s | 10.857625ms | 2274 token(s) | 18.079263709s | 125.78 tokens/s | 242 token(s) | 10.090992541s | 23.98 tokens/s |
| minicpm-v:8b | 111 | 689 | 17.26708725s | 20.33875ms | 107 token(s) | 6.264357625s | 17.08 tokens/s | 225 token(s) | 10.981260792s | 20.49 tokens/s |
| qwen2.5vl:3b | 23 | 214 | 4.921888084s | 22.39225ms | 144 token(s) | 2.901492166s | 49.63 tokens/s | 76 token(s) | 1.996864834s | 38.06 tokens/s |
| qwen2.5vl:7b | 26 | 166 | 6.975697834s | 21.415917ms | 144 token(s) | 2.712148041s | 53.09 tokens/s | 81 token(s) | 4.241220459s | 19.10 tokens/s |
| gemma3:4b | 37 | 322 | 47.901822s | 29.206875ms | 306 token(s) | 42.636782209s | 7.18 tokens/s | 153 token(s) | 5.23476625s | 29.23 tokens/s |
| llava:7b | 88 | 945 | 26.029776041s | 15.577083ms | 627 token(s) | 4.001202291s | 156.70 tokens/s | 413 token(s) | 22.010845209s | 18.76 tokens/s |
| llava-llama3:8b | 4 | 24 | 5.922339333s | 20.612042ms | 624 token(s) | 4.721161208s | 132.17 tokens/s | 21 token(s) | 1.179484958s | 17.80 tokens/s |
| llava-phi3:3.8b | 30 | 193 | 7.979631792s | 14.079583ms | 629 token(s) | 2.967841333s | 211.94 tokens/s | 143 token(s) | 4.996010667s | 28.62 tokens/s |
| bakllava:7b | 4 | 25 | 5.262416042s | 8.483875ms | 631 token(s) | 4.06429425s | 155.25 tokens/s | 24 token(s) | 1.188468s | 20.19 tokens/s |
| moondream:1.8b | 4 | 28 | 5.273929375s | 14.659167ms | 777 token(s) | 4.966628792s | 156.44 tokens/s | 19 token(s) | 290.753875ms | 65.35 tokens/s |
| System | |
| ollama proc | 100% GPU |
| ollama version | 0.9.0 |
| sys arch | arm64 |
| sys processor | arm |
| sys memory | 15G + 1312M |
| sys OS | Darwin 24.5.0 |