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 | 860.854375ms | 13.300625ms | 20 token(s) | 755.623292ms | 26.47 tokens/s | 2 token(s) | 90.9815ms | 21.98 tokens/s |
codellama:7b | 23 | 130 | 2.686167417s | 12.212875ms | 28 token(s) | 1.15061925s | 24.33 tokens/s | 32 token(s) | 1.522740208s | 21.01 tokens/s |
deepcoder:1.5b | 256 | 1651 | 6.183683042s | 18.915459ms | 11 token(s) | 103.520375ms | 106.26 tokens/s | 366 token(s) | 6.060617583s | 60.39 tokens/s |
deepseek-r1:1.5b | 856 | 5625 | 18.816139208s | 20.318625ms | 11 token(s) | 95.441792ms | 115.25 tokens/s | 1087 token(s) | 18.699888958s | 58.13 tokens/s |
deepseek-r1:8b | 494 | 2873 | 38.097525583s | 19.63225ms | 10 token(s) | 370.486083ms | 26.99 tokens/s | 625 token(s) | 37.706826s | 16.58 tokens/s |
dolphin3:8b | 80 | 482 | 7.153430292s | 19.993208ms | 31 token(s) | 1.508764417s | 20.55 tokens/s | 103 token(s) | 5.624162333s | 18.31 tokens/s |
gemma3:1b | 447 | 2984 | 10.906673125s | 28.153042ms | 16 token(s) | 92.875291ms | 172.27 tokens/s | 723 token(s) | 10.785082959s | 67.04 tokens/s |
gemma3:4b | 64 | 363 | 3.838006875s | 27.858583ms | 16 token(s) | 255.762042ms | 62.56 tokens/s | 101 token(s) | 3.553869708s | 28.42 tokens/s |
gemma:2b | 13 | 74 | 472.534417ms | 21.728375ms | 29 token(s) | 118.992709ms | 243.71 tokens/s | 17 token(s) | 331.26725ms | 51.32 tokens/s |
granite3.2-vision:2b | 32 | 205 | 1.732396084s | 12.471084ms | 55 token(s) | 530.718916ms | 103.63 tokens/s | 46 token(s) | 1.188563334s | 38.70 tokens/s |
granite3.3:2b | 74 | 440 | 2.9947345s | 15.664666ms | 51 token(s) | 233.324791ms | 218.58 tokens/s | 115 token(s) | 2.744981792s | 41.89 tokens/s |
llava-llama3:8b | 30 | 162 | 2.800576084s | 21.317417ms | 18 token(s) | 412.132791ms | 43.68 tokens/s | 42 token(s) | 2.366558125s | 17.75 tokens/s |
llava-phi3:3.8b | 104 | 617 | 4.483276666s | 12.830958ms | 18 token(s) | 430.523291ms | 41.81 tokens/s | 129 token(s) | 4.039031959s | 31.94 tokens/s |
llava:7b | 73 | 404 | 4.944177708s | 7.116375ms | 16 token(s) | 421.154833ms | 37.99 tokens/s | 91 token(s) | 4.515139083s | 20.15 tokens/s |
minicpm-v:8b | 11 | 1034 | 11.174099166s | 15.588083ms | 16 token(s) | 584.753ms | 27.36 tokens/s | 217 token(s) | 10.5731755s | 20.52 tokens/s |
mistral:7b | 62 | 352 | 4.849877458s | 14.357875ms | 13 token(s) | 482.736416ms | 26.93 tokens/s | 89 token(s) | 4.351993959s | 20.45 tokens/s |
moondream:1.8b | 1 | 5 | 232.063042ms | 14.999125ms | 14 token(s) | 191.50875ms | 73.10 tokens/s | 3 token(s) | 24.772042ms | 121.10 tokens/s |
qwen2.5-coder:7b | 332 | 2248 | 22.979256625s | 16.611875ms | 37 token(s) | 520.831084ms | 71.04 tokens/s | 422 token(s) | 22.441251041s | 18.80 tokens/s |
qwen2.5vl:3b | 50 | 275 | 2.015582041s | 22.531833ms | 28 token(s) | 280.502667ms | 99.82 tokens/s | 61 token(s) | 1.711994916s | 35.63 tokens/s |
qwen2.5vl:7b | 65 | 373 | 6.871754375s | 24.804584ms | 28 token(s) | 2.068916167s | 13.53 tokens/s | 91 token(s) | 4.777496708s | 19.05 tokens/s |
qwen3:1.7b | 545 | 3157 | 13.712955458s | 20.523041ms | 18 token(s) | 136.215083ms | 132.14 tokens/s | 735 token(s) | 13.555584958s | 54.22 tokens/s |
stable-code:3b | 29 | 181 | 1.383655s | 14.47875ms | 17 token(s) | 186.792792ms | 91.01 tokens/s | 49 token(s) | 1.181552916s | 41.47 tokens/s |
starcoder:7b | 51 | 351 | 4.767853666s | 16.277166ms | 8 token(s) | 287.775375ms | 27.80 tokens/s | 87 token(s) | 4.463140292s | 19.49 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.0 |
sys arch | arm64 |
sys processor | arm |
sys memory | 15G + 1966M |
sys OS | Darwin 24.5.0 |