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 | 1.093577292s | 15.675125ms | 20 token(s) | 1.02471125s | 19.52 tokens/s | 2 token(s) | 52.32525ms | 38.22 tokens/s |
codellama:7b | 86 | 514 | 7.530658041s | 13.591375ms | 28 token(s) | 1.108235417s | 25.27 tokens/s | 127 token(s) | 6.408033125s | 19.82 tokens/s |
deepcoder:1.5b | 108 | 666 | 2.589670167s | 28.719334ms | 11 token(s) | 112.861833ms | 97.46 tokens/s | 142 token(s) | 2.447602709s | 58.02 tokens/s |
deepseek-r1:1.5b | 200 | 1432 | 23.167286167s | 27.073209ms | 11 token(s) | 108.727833ms | 101.17 tokens/s | 1222 token(s) | 23.031002542s | 53.06 tokens/s |
deepseek-r1:8b | 99 | 588 | 1m0.625143166s | 28.110125ms | 10 token(s) | 401.833417ms | 24.89 tokens/s | 895 token(s) | 1m0.19474325s | 14.87 tokens/s |
dolphin-mistral:7b | 103 | 600 | 8.356041875s | 16.630042ms | 36 token(s) | 608.091541ms | 59.20 tokens/s | 139 token(s) | 7.729709042s | 17.98 tokens/s |
dolphin3:8b | 50 | 273 | 4.579101709s | 27.028542ms | 31 token(s) | 861.697792ms | 35.98 tokens/s | 61 token(s) | 3.689712458s | 16.53 tokens/s |
gemma3:1b | 443 | 2845 | 11.485531708s | 53.944083ms | 16 token(s) | 107.655834ms | 148.62 tokens/s | 701 token(s) | 11.323343s | 61.91 tokens/s |
gemma3:4b | 83 | 487 | 4.875548084s | 53.473209ms | 16 token(s) | 252.238917ms | 63.43 tokens/s | 123 token(s) | 4.56924175s | 26.92 tokens/s |
gemma:2b | 18 | 106 | 672.277916ms | 29.114458ms | 29 token(s) | 144.5335ms | 200.65 tokens/s | 23 token(s) | 498.036083ms | 46.18 tokens/s |
granite3.2-vision:2b | 32 | 205 | 2.094847583s | 18.484791ms | 55 token(s) | 840.481625ms | 65.44 tokens/s | 46 token(s) | 1.235223459s | 37.24 tokens/s |
granite3.3:2b | 58 | 367 | 2.76564775s | 18.82575ms | 51 token(s) | 252.137667ms | 202.27 tokens/s | 94 token(s) | 2.49389525s | 37.69 tokens/s |
huihui_ai/baronllm-abliterated:8b | 90 | 533 | 7.859557291s | 29.797ms | 18 token(s) | 504.658208ms | 35.67 tokens/s | 122 token(s) | 7.324519584s | 16.66 tokens/s |
llama3-groq-tool-use:8b | 46 | 255 | 4.464352042s | 30.100167ms | 18 token(s) | 735.03475ms | 24.49 tokens/s | 64 token(s) | 3.698632667s | 17.30 tokens/s |
llama3.2:1b | 96 | 576 | 2.51057025s | 29.632792ms | 33 token(s) | 146.386083ms | 225.43 tokens/s | 122 token(s) | 2.334026375s | 52.27 tokens/s |
llava-llama3:8b | 33 | 188 | 3.368466791s | 29.571791ms | 18 token(s) | 779.642625ms | 23.09 tokens/s | 42 token(s) | 2.558626375s | 16.42 tokens/s |
llava-phi3:3.8b | 81 | 496 | 4.112276209s | 15.589542ms | 18 token(s) | 504.229833ms | 35.70 tokens/s | 106 token(s) | 3.591716958s | 29.51 tokens/s |
llava:7b | 52 | 305 | 4.156201958s | 10.417375ms | 16 token(s) | 374.86575ms | 42.68 tokens/s | 70 token(s) | 3.770345875s | 18.57 tokens/s |
minicpm-v:8b | 5 | 302 | 4.91902475s | 26.131667ms | 16 token(s) | 1.45164025s | 11.02 tokens/s | 65 token(s) | 3.440706125s | 18.89 tokens/s |
mistral:7b | 70 | 414 | 5.851440042s | 13.086417ms | 13 token(s) | 521.111542ms | 24.95 tokens/s | 99 token(s) | 5.316323125s | 18.62 tokens/s |
qwen2.5-coder:7b | 15 | 80 | 1.933192333s | 25.300125ms | 37 token(s) | 580.91425ms | 63.69 tokens/s | 22 token(s) | 1.326484959s | 16.59 tokens/s |
qwen2.5vl:3b | 50 | 275 | 2.402432084s | 39.037125ms | 28 token(s) | 386.880459ms | 72.37 tokens/s | 61 token(s) | 1.975577708s | 30.88 tokens/s |
qwen2.5vl:7b | 65 | 373 | 7.628220709s | 27.57225ms | 28 token(s) | 2.326446708s | 12.04 tokens/s | 91 token(s) | 5.273544042s | 17.26 tokens/s |
qwen3:1.7b | 87 | 490 | 11.469360125s | 29.848417ms | 18 token(s) | 141.394875ms | 127.30 tokens/s | 573 token(s) | 11.297449625s | 50.72 tokens/s |
qwen3:8b | 85 | 504 | 20.998188583s | 28.618875ms | 18 token(s) | 406.3925ms | 44.29 tokens/s | 314 token(s) | 20.562639375s | 15.27 tokens/s |
stable-code:3b | 66 | 587 | 4.958241958s | 17.355583ms | 17 token(s) | 315.728958ms | 53.84 tokens/s | 190 token(s) | 4.624595292s | 41.08 tokens/s |
starcoder:7b | 1 | 4 | 449.796958ms | 20.560375ms | 8 token(s) | 316.928625ms | 25.24 tokens/s | 3 token(s) | 111.56825ms | 26.89 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.3 |
sys arch | arm64 |
sys processor | arm |
sys memory | 14G + 1602M |
sys OS | Darwin 24.5.0 |