Prompt: (raw) (yaml)
words:2 bytes:237
model | words | bytes | total duration |
load duration |
prompt eval count |
prompt eval duration |
prompt eval rate |
eval count |
eval duration |
eval rate |
---|---|---|---|---|---|---|---|---|---|---|
bakllava:7b | 5 | 45 | 2.544879167s | 16.178875ms | 185 token(s) | 2.05324s | 90.10 tokens/s | 10 token(s) | 474.548458ms | 21.07 tokens/s |
codellama:7b | 68 | 389 | 7.796108917s | 15.993333ms | 199 token(s) | 2.630256792s | 75.66 tokens/s | 93 token(s) | 5.147224333s | 18.07 tokens/s |
deepcoder:1.5b | 140 | 968 | 30.973799458s | 27.27025ms | 164 token(s) | 302.4985ms | 542.15 tokens/s | 1635 token(s) | 30.643275333s | 53.36 tokens/s |
deepseek-r1:1.5b | 81 | 506 | 1m35.08399025s | 27.144291ms | 164 token(s) | 286.373958ms | 572.68 tokens/s | 4403 token(s) | 1m34.7699195s | 46.46 tokens/s |
deepseek-r1:8b | 143 | 897 | 27.925168584s | 27.009709ms | 163 token(s) | 1.444168042s | 112.87 tokens/s | 432 token(s) | 26.453391916s | 16.33 tokens/s |
dolphin-mistral:7b | 45 | 272 | 5.242021666s | 12.51725ms | 201 token(s) | 2.035037s | 98.77 tokens/s | 66 token(s) | 3.193750417s | 20.67 tokens/s |
dolphin3:8b | 27 | 167 | 4.029051292s | 27.827459ms | 180 token(s) | 1.937350208s | 92.91 tokens/s | 38 token(s) | 2.063254042s | 18.42 tokens/s |
gemma3:1b | 33 | 196 | 1.015540959s | 53.017084ms | 155 token(s) | 174.874958ms | 886.35 tokens/s | 55 token(s) | 787.113709ms | 69.88 tokens/s |
gemma3:4b | 28 | 399 | 7.829510458s | 52.276167ms | 155 token(s) | 1.060430208s | 146.17 tokens/s | 197 token(s) | 6.716211875s | 29.33 tokens/s |
gemma:2b | 26 | 160 | 1.059459792s | 29.981417ms | 164 token(s) | 360.492666ms | 454.93 tokens/s | 31 token(s) | 668.424459ms | 46.38 tokens/s |
granite3.2-vision:2b | 20 | 122 | 1.879474375s | 19.872125ms | 187 token(s) | 998.498959ms | 187.28 tokens/s | 35 token(s) | 860.372958ms | 40.68 tokens/s |
granite3.3:2b | 37 | 317 | 3.294317333s | 20.294708ms | 183 token(s) | 527.61525ms | 346.84 tokens/s | 114 token(s) | 2.745784666s | 41.52 tokens/s |
huihui_ai/baronllm-abliterated:8b | 282 | 2063 | 24.487597333s | 30.927958ms | 167 token(s) | 1.440919166s | 115.90 tokens/s | 407 token(s) | 23.015165375s | 17.68 tokens/s |
llama3-groq-tool-use:8b | 20 | 111 | 3.137838167s | 30.667667ms | 167 token(s) | 1.641176334s | 101.76 tokens/s | 29 token(s) | 1.465170291s | 19.79 tokens/s |
llama3.2:1b | 6 | 43 | ||||||||
llava-llama3:8b | 106 | 683 | 11.444585s | 29.987208ms | 167 token(s) | 4.094308291s | 40.79 tokens/s | 124 token(s) | 7.319464959s | 16.94 tokens/s |
llava-phi3:3.8b | 53 | 329 | 3.413783625s | 15.877333ms | 189 token(s) | 1.091263958s | 173.19 tokens/s | 74 token(s) | 2.30583975s | 32.09 tokens/s |
llava:7b | 34 | 418 | 14.554349584s | 15.962917ms | 181 token(s) | 2.556812584s | 70.79 tokens/s | 226 token(s) | 11.98063375s | 18.86 tokens/s |
minicpm-v:8b | 19 | 365 | 6.52999625s | 27.196125ms | 169 token(s) | 2.5500835s | 66.27 tokens/s | 80 token(s) | 3.95175775s | 20.24 tokens/s |
mistral:7b | 35 | 241 | 5.437518917s | 14.872917ms | 178 token(s) | 1.919783875s | 92.72 tokens/s | 72 token(s) | 3.502075209s | 20.56 tokens/s |
qwen2.5-coder:7b | 40 | 240 | 4.412762166s | 28.468041ms | 190 token(s) | 1.398392792s | 135.87 tokens/s | 55 token(s) | 2.985236583s | 18.42 tokens/s |
qwen2.5vl:3b | 86 | 751 | 8.609282583s | 28.389042ms | 181 token(s) | 962.572708ms | 188.04 tokens/s | 268 token(s) | 7.617757958s | 35.18 tokens/s |
qwen2.5vl:7b | 60 | 390 | 6.993707459s | 38.718459ms | 181 token(s) | 2.412182167s | 75.04 tokens/s | 80 token(s) | 4.542014875s | 17.61 tokens/s |
qwen3:1.7b | 6 | 43 | ||||||||
qwen3:8b | 6 | 43 | ||||||||
stable-code:3b | 25 | 276 | 3.757426834s | 18.40875ms | 168 token(s) | 706.866959ms | 237.67 tokens/s | 124 token(s) | 3.031554791s | 40.90 tokens/s |
starcoder:7b | 1 | 8 | 1.169898916s | 17.989458ms | 140 token(s) | 995.278208ms | 140.66 tokens/s | 4 token(s) | 155.976125ms | 25.64 tokens/s |
System | |
ollama proc | 100% GPU |
ollama version | 0.9.3 |
sys arch | arm64 |
sys processor | arm |
sys memory | 14G + 2713M |
sys OS | Darwin 24.5.0 |