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 | 825.36175ms | 16.32825ms | 25 token(s) | 758.457792ms | 32.96 tokens/s | 2 token(s) | 49.631167ms | 40.30 tokens/s |
codellama:7b | 8 | 44 | 1.969373541s | 10.939833ms | 33 token(s) | 1.190268333s | 27.72 tokens/s | 16 token(s) | 767.607042ms | 20.84 tokens/s |
deepcoder:1.5b | 19 | 132 | 14.554334583s | 28.050375ms | 15 token(s) | 103.692041ms | 144.66 tokens/s | 852 token(s) | 14.422028334s | 59.08 tokens/s |
deepseek-r1:1.5b | 78 | 486 | 3.778607625s | 29.057667ms | 15 token(s) | 109.453666ms | 137.04 tokens/s | 216 token(s) | 3.639602292s | 59.35 tokens/s |
deepseek-r1:8b | 6 | 43 | ||||||||
dolphin-mistral:7b | 8 | 42 | 1.752819916s | 9.6245ms | 41 token(s) | 1.009713375s | 40.61 tokens/s | 16 token(s) | 732.934375ms | 21.83 tokens/s |
dolphin3:8b | 8 | 43 | 2.872770458s | 27.115416ms | 35 token(s) | 1.671073042s | 20.94 tokens/s | 15 token(s) | 1.173902416s | 12.78 tokens/s |
gemma3:1b | 8 | 48 | 340.664584ms | 51.532584ms | 20 token(s) | 93.146375ms | 214.72 tokens/s | 14 token(s) | 195.340459ms | 71.67 tokens/s |
gemma3:4b | 18 | 95 | 1.642798875s | 51.0665ms | 20 token(s) | 588.049458ms | 34.01 tokens/s | 27 token(s) | 1.003077125s | 26.92 tokens/s |
gemma:2b | 18 | 88 | 824.127959ms | 28.932625ms | 33 token(s) | 170.941916ms | 193.05 tokens/s | 31 token(s) | 623.500667ms | 49.72 tokens/s |
granite3.2-vision:2b | 8 | 44 | 1.211016334s | 18.658375ms | 59 token(s) | 842.331708ms | 70.04 tokens/s | 16 token(s) | 349.3015ms | 45.81 tokens/s |
granite3.3:2b | 15 | 106 | 1.191745417s | 20.80125ms | 55 token(s) | 241.491792ms | 227.75 tokens/s | 42 token(s) | 928.690208ms | 45.22 tokens/s |
huihui_ai/baronllm-abliterated:8b | 8 | 44 | 1.247293s | 31.099291ms | 22 token(s) | 441.558166ms | 49.82 tokens/s | 14 token(s) | 773.996292ms | 18.09 tokens/s |
llama3-groq-tool-use:8b | 8 | 43 | 1.571783292s | 30.065625ms | 22 token(s) | 720.757333ms | 30.52 tokens/s | 15 token(s) | 820.445834ms | 18.28 tokens/s |
llama3.2:1b | 8 | 43 | 419.661958ms | 31.541791ms | 37 token(s) | 145.494125ms | 254.31 tokens/s | 15 token(s) | 242.180542ms | 61.94 tokens/s |
llava-llama3:8b | 8 | 46 | 2.472120541s | 30.613375ms | 24 token(s) | 1.665999583s | 14.41 tokens/s | 15 token(s) | 774.925833ms | 19.36 tokens/s |
llava-phi3:3.8b | 18 | 97 | 1.463518583s | 15.32325ms | 23 token(s) | 484.091958ms | 47.51 tokens/s | 29 token(s) | 963.26125ms | 30.11 tokens/s |
llava:7b | 9 | 54 | 1.161610667s | 16.885417ms | 21 token(s) | 374.265667ms | 56.11 tokens/s | 17 token(s) | 769.628166ms | 22.09 tokens/s |
minicpm-v:8b | 9 | 51 | 1.97338s | 24.816542ms | 20 token(s) | 1.113655167s | 17.96 tokens/s | 17 token(s) | 834.369792ms | 20.37 tokens/s |
mistral:7b | 9 | 51 | 1.3911795s | 17.042417ms | 18 token(s) | 570.04975ms | 31.58 tokens/s | 16 token(s) | 803.243708ms | 19.92 tokens/s |
qwen2.5-coder:7b | 6 | 40 | 1.455542208s | 27.755666ms | 41 token(s) | 572.465667ms | 71.62 tokens/s | 15 token(s) | 854.719125ms | 17.55 tokens/s |
qwen2.5vl:3b | 8 | 43 | 818.307542ms | 28.742ms | 32 token(s) | 411.077167ms | 77.84 tokens/s | 15 token(s) | 377.932666ms | 39.69 tokens/s |
qwen2.5vl:7b | 6 | 42 | 3.002568083s | 28.83925ms | 32 token(s) | 2.27597625s | 14.06 tokens/s | 14 token(s) | 697.139708ms | 20.08 tokens/s |
qwen3:1.7b | 81 | 484 | 14.15971175s | 28.236125ms | 22 token(s) | 126.414708ms | 174.03 tokens/s | 762 token(s) | 14.004524708s | 54.41 tokens/s |
qwen3:8b | 33 | 238 | 31.032145084s | 27.843625ms | 22 token(s) | 403.538625ms | 54.52 tokens/s | 493 token(s) | 30.59996875s | 16.11 tokens/s |
stable-code:3b | 105 | 686 | 5.578522916s | 17.071833ms | 23 token(s) | 324.289666ms | 70.92 tokens/s | 229 token(s) | 5.23648775s | 43.73 tokens/s |
starcoder:7b | 2667 | 14425 | 4m49.941031291s | 19.253375ms | 14 token(s) | 328.250166ms | 42.65 tokens/s | 4150 token(s) | 4m49.592826125s | 14.33 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.3 |
sys arch | arm64 |
sys processor | arm |
sys memory | 15G + 519M |
sys OS | Darwin 24.5.0 |