Prompt: (raw) (yaml)
words:3130 bytes:31962
model | words | bytes | total duration |
load duration |
prompt eval count |
prompt eval duration |
prompt eval rate |
eval count |
eval duration |
eval rate |
---|---|---|---|---|---|---|---|---|---|---|
codellama:7b | 6 | 44 | ||||||||
cogito:3b | 298 | 2192 | 1m10.335475167s | 29.404375ms | 9454 token(s) | 39.609354833s | 238.68 tokens/s | 431 token(s) | 30.695814875s | 14.04 tokens/s |
cogito:8b | 270 | 1956 | 2m5.265967125s | 31.281791ms | 9454 token(s) | 1m20.63489875s | 117.24 tokens/s | 365 token(s) | 44.598852458s | 8.18 tokens/s |
deepcoder:1.5b | 251 | 1799 | 1m2.357411625s | 28.717792ms | 9486 token(s) | 19.503133792s | 486.38 tokens/s | 1058 token(s) | 42.824729958s | 24.71 tokens/s |
deepseek-r1:1.5b | 155 | 2064 | 38.772701667s | 29.122917ms | 9486 token(s) | 19.659783417s | 482.51 tokens/s | 481 token(s) | 19.082892666s | 25.21 tokens/s |
deepseek-r1:14b | 6 | 44 | ||||||||
deepseek-r1:8b | 6 | 44 | ||||||||
dolphin-mistral:7b | 241 | 1480 | 2m17.311102333s | 14.051542ms | 11216 token(s) | 1m36.135333958s | 116.67 tokens/s | 307 token(s) | 41.160795709s | 7.46 tokens/s |
dolphin3:8b | 343 | 2224 | 2m17.596174417s | 30.353959ms | 9467 token(s) | 1m23.533245625s | 113.33 tokens/s | 418 token(s) | 54.031815666s | 7.74 tokens/s |
gemma3:1b | 603 | 4393 | 25.281471375s | 52.187167ms | 10415 token(s) | 9.036307s | 1152.57 tokens/s | 931 token(s) | 16.192252542s | 57.50 tokens/s |
gemma3:4b | 770 | 5355 | 1m27.473120375s | 52.282792ms | 10415 token(s) | 34.624831041s | 300.80 tokens/s | 1226 token(s) | 52.794952s | 23.22 tokens/s |
gemma3n:e2b | 737 | 5368 | 2m34.713787792s | 50.837792ms | 10994 token(s) | 1m47.353315833s | 102.41 tokens/s | 1267 token(s) | 47.308858542s | 26.78 tokens/s |
gemma3n:e4b | 766 | 5527 | 3m15.347561583s | 53.39325ms | 10994 token(s) | 2m12.591910291s | 82.92 tokens/s | 1208 token(s) | 1m2.700452459s | 19.27 tokens/s |
gemma:2b | 250 | 2711 | 31.753262542s | 31.495542ms | 8192 token(s) | 15.812352042s | 518.08 tokens/s | 516 token(s) | 15.908586125s | 32.44 tokens/s |
granite3.3:2b | 436 | 3343 | 2m8.455306125s | 18.347334ms | 9824 token(s) | 50.097508584s | 196.10 tokens/s | 728 token(s) | 1m18.338251375s | 9.29 tokens/s |
granite3.3:8b | 606 | 4432 | 3m57.261146209s | 18.477334ms | 9824 token(s) | 1m39.958607584s | 98.28 tokens/s | 917 token(s) | 2m17.282940541s | 6.68 tokens/s |
hermes3:8b | 472 | 3153 | 2m28.147392875s | 32.168917ms | 9453 token(s) | 1m14.480527042s | 126.92 tokens/s | 613 token(s) | 1m13.6333405s | 8.33 tokens/s |
llama3.1:8b-instruct-q4_1 | 354 | 2365 | 2m11.561272875s | 34.841542ms | 9454 token(s) | 1m13.447547041s | 128.72 tokens/s | 467 token(s) | 58.07805125s | 8.04 tokens/s |
llama3.2:1b | 475 | 3227 | 50.17898275s | 31.723542ms | 9469 token(s) | 18.043346125s | 524.79 tokens/s | 648 token(s) | 32.103027875s | 20.19 tokens/s |
llama3.2:3b | 373 | 2608 | 1m15.32632425s | 32.300667ms | 9469 token(s) | 39.776010667s | 238.06 tokens/s | 498 token(s) | 35.516824083s | 14.02 tokens/s |
llava-llama3:8b | 403 | 3007 | 1m24.407606334s | 32.455542ms | 4096 token(s) | 29.054442417s | 140.98 tokens/s | 670 token(s) | 55.319785917s | 12.11 tokens/s |
llava-phi3:3.8b | 110 | 1203 | 45.240111125s | 12.23575ms | 4096 token(s) | 18.062089s | 226.77 tokens/s | 429 token(s) | 27.164732833s | 15.79 tokens/s |
llava:7b | 507 | 3359 | 3m7.078534459s | 12.79125ms | 11196 token(s) | 1m32.811280375s | 120.63 tokens/s | 729 token(s) | 1m34.253031708s | 7.73 tokens/s |
minicpm-v:8b | 182 | 1186 | 1m28.707654125s | 27.85775ms | 9526 token(s) | 1m5.872496166s | 144.61 tokens/s | 230 token(s) | 22.806308084s | 10.08 tokens/s |
mistral:7b | 302 | 1874 | 2m26.048351167s | 13.154292ms | 11193 token(s) | 1m32.336201416s | 121.22 tokens/s | 420 token(s) | 53.697713375s | 7.82 tokens/s |
mistral:7b-instruct | 272 | 1718 | 2m28.145693708s | 13.9595ms | 11192 token(s) | 1m32.179438625s | 121.42 tokens/s | 437 token(s) | 55.95085925s | 7.81 tokens/s |
qwen2.5-coder:7b | 513 | 3410 | 2m24.465752875s | 25.932208ms | 9518 token(s) | 1m11.232226834s | 133.62 tokens/s | 696 token(s) | 1m13.206609875s | 9.51 tokens/s |
qwen2.5vl:3b | 511 | 3742 | 1m37.853286583s | 31.260625ms | 9511 token(s) | 38.730018459s | 245.57 tokens/s | 849 token(s) | 59.091054125s | 14.37 tokens/s |
qwen2.5vl:7b | 6 | 44 | ||||||||
qwen3:0.6b | 7 | 32140 | ||||||||
qwen3:1.7b | 509 | 3708 | 1m42.388086708s | 29.125083ms | 9493 token(s) | 23.491653833s | 404.10 tokens/s | 1535 token(s) | 1m18.866199333s | 19.46 tokens/s |
qwen3:14b | 6 | 44 | ||||||||
qwen3:4b | 0 | 1 | 7m41.0294345s | 27.101875ms | 9493 token(s) | 1m0.911861583s | 155.85 tokens/s | 3107 token(s) | 6m40.089607125s | 7.77 tokens/s |
qwen3:8b | 6 | 44 | ||||||||
smollm2:1.7b | 188 | 1597 | 1m4.96424725s | 16.752584ms | 8192 token(s) | 24.713669917s | 331.48 tokens/s | 548 token(s) | 40.232489333s | 13.62 tokens/s |
smollm2:135m | 58 | 511 | 26.971959375s | 18.462666ms | 8192 token(s) | 5.810105292s | 1409.96 tokens/s | 934 token(s) | 21.142385083s | 44.18 tokens/s |
smollm2:360m | 135 | 901 | 19.0997465s | 17.077792ms | 8192 token(s) | 10.444778833s | 784.32 tokens/s | 220 token(s) | 8.636990125s | 25.47 tokens/s |
System | |
Ollama proc | 100% GPU |
Ollama context | 16384 |
Ollama version | 0.9.7-rc0 |
Multirun timeout | 600 seconds |
Sys arch | arm64 |
Sys processor | arm |
sys memory | 12G + 747M |
Sys OS | Darwin 24.5.0 |