Prompt: (raw) (yaml)
words:7 bytes:39
model | words | bytes | total duration |
load duration |
prompt eval count |
prompt eval duration |
prompt eval rate |
eval count |
eval duration |
eval rate |
---|---|---|---|---|---|---|---|---|---|---|
bakllava:7b | 1 | 3 | 488.127125ms | 13.962333ms | 25 token(s) | 425.205042ms | 58.80 tokens/s | 2 token(s) | 47.953083ms | 41.71 tokens/s |
codellama:7b | 8 | 44 | 1.476173042s | 11.670292ms | 33 token(s) | 650.330375ms | 50.74 tokens/s | 16 token(s) | 813.416083ms | 19.67 tokens/s |
deepcoder:1.5b | 496 | 2332 | 12.799791875s | 20.148333ms | 15 token(s) | 98.009875ms | 153.05 tokens/s | 753 token(s) | 12.681017416s | 59.38 tokens/s |
deepseek-r1:1.5b | 154 | 906 | 5.284500667s | 19.555042ms | 15 token(s) | 108.634542ms | 138.08 tokens/s | 295 token(s) | 5.155539208s | 57.22 tokens/s |
deepseek-r1:8b | 1824 | 10116 | 3m24.372772833s | 19.581333ms | 14 token(s) | 388.170875ms | 36.07 tokens/s | 2942 token(s) | 3m23.964416125s | 14.42 tokens/s |
dolphin3:8b | 8 | 42 | 1.558867167s | 20.721417ms | 35 token(s) | 699.043166ms | 50.07 tokens/s | 16 token(s) | 838.26775ms | 19.09 tokens/s |
gemma3:1b | 8 | 52 | 372.332834ms | 26.427584ms | 20 token(s) | 110.381375ms | 181.19 tokens/s | 16 token(s) | 234.991792ms | 68.09 tokens/s |
gemma3:4b | 18 | 99 | 1.786310458s | 28.262333ms | 20 token(s) | 327.612833ms | 61.05 tokens/s | 29 token(s) | 1.429888542s | 20.28 tokens/s |
gemma:2b | 18 | 92 | 731.575958ms | 22.446708ms | 33 token(s) | 166.781ms | 197.86 tokens/s | 27 token(s) | 541.848958ms | 49.83 tokens/s |
granite3.2-vision:2b | 8 | 44 | 813.971292ms | 12.523708ms | 59 token(s) | 459.868042ms | 128.30 tokens/s | 16 token(s) | 340.933333ms | 46.93 tokens/s |
granite3.3:2b | 10 | 69 | 640.768292ms | 15.886833ms | 55 token(s) | 263.459958ms | 208.76 tokens/s | 17 token(s) | 360.544792ms | 47.15 tokens/s |
llava-llama3:8b | 8 | 46 | 1.219075292s | 20.77175ms | 24 token(s) | 421.087042ms | 57.00 tokens/s | 15 token(s) | 776.656875ms | 19.31 tokens/s |
llava-phi3:3.8b | 7 | 43 | 850.027792ms | 13.555208ms | 23 token(s) | 441.896416ms | 52.05 tokens/s | 14 token(s) | 393.582375ms | 35.57 tokens/s |
llava:7b | 10 | 64 | 1.638644333s | 15.760208ms | 21 token(s) | 407.666292ms | 51.51 tokens/s | 25 token(s) | 1.214337041s | 20.59 tokens/s |
minicpm-v:8b | 8 | 43 | 1.042232292s | 16.410167ms | 20 token(s) | 348.756583ms | 57.35 tokens/s | 15 token(s) | 676.464875ms | 22.17 tokens/s |
mistral:7b | 9 | 51 | 1.162508041s | 13.828833ms | 18 token(s) | 433.619875ms | 41.51 tokens/s | 16 token(s) | 714.005792ms | 22.41 tokens/s |
moondream:1.8b | 0 | 2 | 186.801083ms | 14.495208ms | 20 token(s) | 170.993167ms | 116.96 tokens/s | 1 token(s) | 281.583µs | 3551.35 tokens/s |
qwen2.5-coder:7b | 8 | 44 | 1.304806792s | 16.681292ms | 41 token(s) | 504.333708ms | 81.30 tokens/s | 16 token(s) | 783.238292ms | 20.43 tokens/s |
qwen2.5vl:3b | 8 | 43 | 867.227292ms | 22.013084ms | 32 token(s) | 470.729292ms | 67.98 tokens/s | 15 token(s) | 373.918292ms | 40.12 tokens/s |
qwen2.5vl:7b | 6 | 42 | 2.5705095s | 21.820875ms | 32 token(s) | 1.869100334s | 17.12 tokens/s | 14 token(s) | 678.988083ms | 20.62 tokens/s |
qwen3:1.7b | 511 | 2714 | 16.54532775s | 19.919917ms | 22 token(s) | 132.419292ms | 166.14 tokens/s | 884 token(s) | 16.39229925s | 53.93 tokens/s |
stable-code:3b | 90 | 600 | 3.841983834s | 13.044125ms | 23 token(s) | 230.54575ms | 99.76 tokens/s | 157 token(s) | 3.597685125s | 43.64 tokens/s |
starcoder:7b | 12 | 59 | 1.082396542s | 17.423167ms | 14 token(s) | 308.411542ms | 45.39 tokens/s | 16 token(s) | 755.799875ms | 21.17 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.0 |
sys arch | arm64 |
sys processor | arm |
sys memory | 14G + 1801M |
sys OS | Darwin 24.5.0 |