Prompt: (raw) (yaml)
words:6 bytes:30
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 | 584.017ms | 11.9745ms | 20 token(s) | 513.868959ms | 38.92 tokens/s | 2 token(s) | 57.101ms | 35.03 tokens/s |
codellama:7b | 35 | 188 | 3.995812333s | 13.240166ms | 28 token(s) | 1.411208958s | 19.84 tokens/s | 45 token(s) | 2.569252917s | 17.51 tokens/s |
deepcoder:1.5b | 143 | 950 | 4.049782542s | 19.730833ms | 11 token(s) | 114.561667ms | 96.02 tokens/s | 201 token(s) | 3.914831625s | 51.34 tokens/s |
deepseek-r1:1.5b | 472 | 2798 | 11.11515875s | 18.792792ms | 11 token(s) | 99.842541ms | 110.17 tokens/s | 580 token(s) | 10.995821875s | 52.75 tokens/s |
deepseek-r1:8b | 1332 | 7933 | 2m16.380028458s | 19.349292ms | 10 token(s) | 555.419208ms | 18.00 tokens/s | 1785 token(s) | 2m15.80451675s | 13.14 tokens/s |
dolphin3:8b | 57 | 328 | 5.638696708s | 21.059542ms | 31 token(s) | 1.138247958s | 27.23 tokens/s | 69 token(s) | 4.478410042s | 15.41 tokens/s |
gemma3:1b | 402 | 2850 | 12.164427334s | 31.14575ms | 16 token(s) | 117.728709ms | 135.91 tokens/s | 714 token(s) | 12.014879208s | 59.43 tokens/s |
gemma3:4b | 61 | 355 | 4.1494635s | 30.550958ms | 16 token(s) | 258.092916ms | 61.99 tokens/s | 97 token(s) | 3.860114042s | 25.13 tokens/s |
gemma:2b | 40 | 229 | 1.557398042s | 21.6405ms | 29 token(s) | 146.20475ms | 198.35 tokens/s | 52 token(s) | 1.388858208s | 37.44 tokens/s |
granite3.2-vision:2b | 32 | 205 | 2.411226875s | 16.023125ms | 55 token(s) | 1.147181375s | 47.94 tokens/s | 46 token(s) | 1.246795209s | 36.89 tokens/s |
granite3.3:2b | 32 | 206 | 1.876638041s | 15.350375ms | 51 token(s) | 262.300375ms | 194.43 tokens/s | 56 token(s) | 1.598109834s | 35.04 tokens/s |
llava-llama3:8b | 32 | 193 | 3.901450667s | 20.315709ms | 18 token(s) | 1.279293083s | 14.07 tokens/s | 41 token(s) | 2.60120225s | 15.76 tokens/s |
llava-phi3:3.8b | 211 | 1290 | 12.760278708s | 10.372625ms | 18 token(s) | 553.382542ms | 32.53 tokens/s | 334 token(s) | 12.194763375s | 27.39 tokens/s |
llava:7b | 72 | 394 | 6.027066584s | 11.047459ms | 16 token(s) | 439.791125ms | 36.38 tokens/s | 98 token(s) | 5.575169291s | 17.58 tokens/s |
minicpm-v:8b | 3 | 567 | 8.062082834s | 21.600084ms | 16 token(s) | 1.619916584s | 9.88 tokens/s | 113 token(s) | 6.419751083s | 17.60 tokens/s |
mistral:7b | 64 | 404 | 5.942051667s | 12.667125ms | 13 token(s) | 487.949708ms | 26.64 tokens/s | 94 token(s) | 5.440611584s | 17.28 tokens/s |
moondream:1.8b | 1 | 5 | 239.216917ms | 16.641875ms | 14 token(s) | 192.480333ms | 72.73 tokens/s | 3 token(s) | 29.198875ms | 102.74 tokens/s |
qwen2.5-coder:7b | 40 | 222 | 3.647847458s | 19.860791ms | 37 token(s) | 571.797208ms | 64.71 tokens/s | 48 token(s) | 3.055464459s | 15.71 tokens/s |
qwen2.5vl:3b | 50 | 275 | 2.38604725s | 20.185125ms | 28 token(s) | 420.101583ms | 66.65 tokens/s | 61 token(s) | 1.945080917s | 31.36 tokens/s |
qwen2.5vl:7b | 65 | 373 | 8.067472291s | 17.814166ms | 28 token(s) | 2.492010542s | 11.24 tokens/s | 91 token(s) | 5.556891958s | 16.38 tokens/s |
qwen3:1.7b | 446 | 2643 | 14.349376709s | 22.042834ms | 18 token(s) | 153.329833ms | 117.39 tokens/s | 676 token(s) | 14.173231125s | 47.70 tokens/s |
stable-code:3b | 34 | 188 | 1.588772791s | 11.658041ms | 17 token(s) | 217.838083ms | 78.04 tokens/s | 45 token(s) | 1.358564208s | 33.12 tokens/s |
starcoder:7b | 1008 | 11511 | 4m50.801551958s | 16.629375ms | 8 token(s) | 321.218584ms | 24.91 tokens/s | 3767 token(s) | 4m50.462322541s | 12.97 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.0 |
sys arch | arm64 |
sys processor | arm |
sys memory | 15G + 1023M |
sys OS | Darwin 24.5.0 |