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 |
---|---|---|---|---|---|---|---|---|---|---|
codellama:7b | 58 | 359 | 4.549390167s | 9.890542ms | 28 token(s) | 632.020834ms | 44.30 tokens/s | 77 token(s) | 3.907046833s | 19.71 tokens/s |
cogito:8b | 51 | 290 | 6.099706208s | 29.214792ms | 18 token(s) | 389.872667ms | 46.17 tokens/s | 65 token(s) | 5.680162167s | 11.44 tokens/s |
deepcoder:1.5b | 94 | 598 | 2.88187525s | 24.654208ms | 11 token(s) | 149.125625ms | 73.76 tokens/s | 116 token(s) | 2.707668208s | 42.84 tokens/s |
deepseek-r1:1.5b | 242 | 1735 | 25.759602083s | 27.992667ms | 11 token(s) | 165.425917ms | 66.50 tokens/s | 1158 token(s) | 25.565746916s | 45.29 tokens/s |
deepseek-r1:8b | 125 | 710 | 1m6.783342042s | 28.429167ms | 10 token(s) | 498.354083ms | 20.07 tokens/s | 770 token(s) | 1m6.256065s | 11.62 tokens/s |
dolphin-mistral:7b | 143 | 861 | 13.325074292s | 18.098625ms | 36 token(s) | 573.695792ms | 62.75 tokens/s | 198 token(s) | 12.732551167s | 15.55 tokens/s |
dolphin3:8b | 139 | 822 | 15.233688542s | 29.258792ms | 31 token(s) | 464.996875ms | 66.67 tokens/s | 175 token(s) | 14.738975917s | 11.87 tokens/s |
gemma3:1b | 480 | 3155 | 14.994355917s | 51.445875ms | 16 token(s) | 109.859917ms | 145.64 tokens/s | 775 token(s) | 14.832651458s | 52.25 tokens/s |
gemma3:4b | 67 | 378 | 5.295508375s | 51.090125ms | 16 token(s) | 498.915875ms | 32.07 tokens/s | 103 token(s) | 4.745120708s | 21.71 tokens/s |
gemma3n:e2b | 109 | 646 | 5.71328625s | 51.44225ms | 16 token(s) | 515.361708ms | 31.05 tokens/s | 146 token(s) | 5.145840042s | 28.37 tokens/s |
gemma:2b | 24 | 152 | 961.752834ms | 28.809209ms | 29 token(s) | 353.113209ms | 82.13 tokens/s | 27 token(s) | 579.298666ms | 46.61 tokens/s |
granite3.3:2b | 43 | 282 | 2.031445334s | 21.960667ms | 51 token(s) | 237.802ms | 214.46 tokens/s | 67 token(s) | 1.770956292s | 37.83 tokens/s |
hermes3:8b | 139 | 815 | 12.202415167s | 32.185167ms | 17 token(s) | 485.760375ms | 35.00 tokens/s | 172 token(s) | 11.684041333s | 14.72 tokens/s |
llama3.2:1b | 87 | 513 | 2.1452305s | 30.041292ms | 33 token(s) | 173.610709ms | 190.08 tokens/s | 102 token(s) | 1.941126291s | 52.55 tokens/s |
llama3.2:3b | 89 | 516 | 4.078803542s | 31.245875ms | 33 token(s) | 267.92125ms | 123.17 tokens/s | 110 token(s) | 3.779209875s | 29.11 tokens/s |
llava-llama3:8b | 55 | 306 | 4.843835917s | 31.225584ms | 18 token(s) | 402.286833ms | 44.74 tokens/s | 65 token(s) | 4.409876292s | 14.74 tokens/s |
llava-phi3:3.8b | 166 | 854 | 9.508191333s | 14.630666ms | 18 token(s) | 316.3275ms | 56.90 tokens/s | 218 token(s) | 9.176707667s | 23.76 tokens/s |
llava:7b | 31 | 199 | 2.734139625s | 16.4905ms | 16 token(s) | 339.818541ms | 47.08 tokens/s | 47 token(s) | 2.377248417s | 19.77 tokens/s |
minicpm-v:8b | 149 | 879 | 12.161442333s | 24.335417ms | 16 token(s) | 415.672125ms | 38.49 tokens/s | 189 token(s) | 11.721021125s | 16.12 tokens/s |
mistral:7b | 44 | 269 | 3.702299541s | 16.466ms | 13 token(s) | 373.825542ms | 34.78 tokens/s | 64 token(s) | 3.311327833s | 19.33 tokens/s |
qwen2.5-coder:7b | 87 | 545 | 8.276333334s | 28.178375ms | 37 token(s) | 544.516833ms | 67.95 tokens/s | 105 token(s) | 7.703201709s | 13.63 tokens/s |
qwen2.5vl:3b | 50 | 275 | 2.456435042s | 32.770792ms | 28 token(s) | 273.828292ms | 102.25 tokens/s | 61 token(s) | 2.149459625s | 28.38 tokens/s |
qwen2.5vl:7b | 65 | 373 | 9.35533875s | 29.41925ms | 28 token(s) | 1.487622333s | 18.82 tokens/s | 91 token(s) | 7.837956542s | 11.61 tokens/s |
qwen3:0.6b | 43 | 246 | 2.371619625s | 28.578208ms | 18 token(s) | 116.363291ms | 154.69 tokens/s | 192 token(s) | 2.22630925s | 86.24 tokens/s |
qwen3:1.7b | 181 | 1098 | 18.743497708s | 26.9615ms | 18 token(s) | 124.131166ms | 145.01 tokens/s | 740 token(s) | 18.591926459s | 39.80 tokens/s |
qwen3:4b | 120 | 690 | 31.897216833s | 24.539208ms | 18 token(s) | 228.652625ms | 78.72 tokens/s | 641 token(s) | 31.643562083s | 20.26 tokens/s |
qwen3:8b | 38 | 217 | 21.911690916s | 26.85125ms | 18 token(s) | 1.805089042s | 9.97 tokens/s | 248 token(s) | 20.079361458s | 12.35 tokens/s |
smollm2:1.7b | 61 | 383 | 2.050757041s | 21.8865ms | 37 token(s) | 233.731333ms | 158.30 tokens/s | 71 token(s) | 1.794520042s | 39.56 tokens/s |
smollm2:135m | 245 | 1358 | 2.271980875s | 22.167792ms | 38 token(s) | 47.262333ms | 804.02 tokens/s | 336 token(s) | 2.202004s | 152.59 tokens/s |
smollm2:360m | 61 | 387 | 979.401833ms | 22.896875ms | 38 token(s) | 114.502917ms | 331.87 tokens/s | 75 token(s) | 841.367708ms | 89.14 tokens/s |
stable-code:3b | 53 | 321 | 2.011896708s | 23.611833ms | 17 token(s) | 226.472917ms | 75.06 tokens/s | 68 token(s) | 1.76119775s | 38.61 tokens/s |
starcoder:7b | 97 | 737 | 12.470546958s | 19.50625ms | 8 token(s) | 294.7385ms | 27.14 tokens/s | 161 token(s) | 12.155830708s | 13.24 tokens/s |
System | |
Ollama proc | 100% GPU 100% GPU |
Ollama version | 0.9.5 |
sys arch | arm64 |
sys processor | arm |
sys memory | 14G + 1338M |
sys OS | Darwin 24.5.0 |