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 | 1.08538275s | 10.913334ms | 25 token(s) | 1.015119542s | 24.63 tokens/s | 2 token(s) | 58.428708ms | 34.23 tokens/s |
codellama:7b | 8 | 44 | 2.212311875s | 15.179042ms | 33 token(s) | 1.378839625s | 23.93 tokens/s | 16 token(s) | 816.845583ms | 19.59 tokens/s |
deepcoder:1.5b | 712 | 3470 | 21.783105875s | 19.245334ms | 15 token(s) | 104.237ms | 143.90 tokens/s | 1121 token(s) | 21.658924875s | 51.76 tokens/s |
deepseek-r1:1.5b | 244 | 1277 | 7.805784875s | 21.080166ms | 15 token(s) | 156.88175ms | 95.61 tokens/s | 405 token(s) | 7.626609791s | 53.10 tokens/s |
deepseek-r1:8b | 3013 | 18640 | ||||||||
dolphin3:8b | 8 | 45 | 1.323235458s | 15.972917ms | 35 token(s) | 579.944958ms | 60.35 tokens/s | 14 token(s) | 726.746708ms | 19.26 tokens/s |
gemma3:1b | 8 | 52 | 424.908541ms | 27.622625ms | 20 token(s) | 111.787917ms | 178.91 tokens/s | 16 token(s) | 284.878917ms | 56.16 tokens/s |
gemma3:4b | 18 | 97 | 1.340475333s | 28.002833ms | 20 token(s) | 251.848125ms | 79.41 tokens/s | 29 token(s) | 1.060015084s | 27.36 tokens/s |
gemma:2b | 18 | 103 | 758.690625ms | 22.393459ms | 33 token(s) | 174.844167ms | 188.74 tokens/s | 28 token(s) | 560.944416ms | 49.92 tokens/s |
granite3.2-vision:2b | 8 | 44 | 734.611958ms | 15.180541ms | 59 token(s) | 379.418625ms | 155.50 tokens/s | 16 token(s) | 339.346292ms | 47.15 tokens/s |
granite3.3:2b | 6 | 42 | 592.626208ms | 17.147292ms | 55 token(s) | 240.982125ms | 228.23 tokens/s | 14 token(s) | 333.66425ms | 41.96 tokens/s |
llava-llama3:8b | 8 | 46 | 1.203957417s | 20.841917ms | 24 token(s) | 417.190459ms | 57.53 tokens/s | 15 token(s) | 765.423541ms | 19.60 tokens/s |
llava-phi3:3.8b | 19 | 115 | 1.626631458s | 14.303833ms | 23 token(s) | 484.265ms | 47.49 tokens/s | 35 token(s) | 1.127273375s | 31.05 tokens/s |
llava:7b | 8 | 49 | 1.094631458s | 10.80025ms | 21 token(s) | 367.954792ms | 57.07 tokens/s | 16 token(s) | 715.246875ms | 22.37 tokens/s |
minicpm-v:8b | 9 | 51 | 1.1222875s | 18.58025ms | 20 token(s) | 333.254ms | 60.01 tokens/s | 17 token(s) | 769.918917ms | 22.08 tokens/s |
mistral:7b | 25 | 145 | 2.57258475s | 12.399125ms | 18 token(s) | 388.001834ms | 46.39 tokens/s | 44 token(s) | 2.171355791s | 20.26 tokens/s |
moondream:1.8b | 0 | 2 | 216.008208ms | 15.604208ms | 20 token(s) | 199.018333ms | 100.49 tokens/s | 1 token(s) | 268.5µs | 3724.39 tokens/s |
qwen2.5-coder:7b | 6 | 40 | 1.245201375s | 19.704709ms | 41 token(s) | 494.50725ms | 82.91 tokens/s | 15 token(s) | 730.304041ms | 20.54 tokens/s |
qwen2.5vl:3b | 8 | 43 | 643.675291ms | 21.603958ms | 32 token(s) | 253.503042ms | 126.23 tokens/s | 15 token(s) | 367.993083ms | 40.76 tokens/s |
qwen2.5vl:7b | 6 | 42 | 1.423394s | 22.221333ms | 32 token(s) | 602.894916ms | 53.08 tokens/s | 14 token(s) | 797.661125ms | 17.55 tokens/s |
qwen3:1.7b | 420 | 2285 | 13.299384416s | 14.690166ms | 22 token(s) | 143.066875ms | 153.77 tokens/s | 717 token(s) | 13.141031375s | 54.56 tokens/s |
stable-code:3b | 75 | 479 | 3.141466s | 13.801917ms | 23 token(s) | 271.453292ms | 84.73 tokens/s | 122 token(s) | 2.855629916s | 42.72 tokens/s |
starcoder:7b | 30 | 207 | 3.150212583s | 16.322125ms | 14 token(s) | 311.110417ms | 45.00 tokens/s | 54 token(s) | 2.82222325s | 19.13 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.0 |
sys arch | arm64 |
sys processor | arm |
sys memory | 14G + 971M |
sys OS | Darwin 24.5.0 |