ollama-multirun: my_hovercraft_is_full_of_eels: 20250712-121106

models: codellama:7b cogito:3b cogito:8b deepcoder:1.5b deepseek-r1:1.5b deepseek-r1:14b deepseek-r1:8b dolphin-mistral:7b dolphin3:8b gemma3:1b gemma3:4b gemma3n:e2b gemma3n:e4b gemma:2b granite3.3:2b granite3.3:8b hermes3:8b llama3.1:8b-instruct-q4_1 llama3.2:1b llama3.2:3b llava-llama3:8b llava-phi3:3.8b llava:7b minicpm-v:8b mistral:7b mistral:7b-instruct qwen2.5-coder:7b qwen2.5vl:3b qwen2.5vl:7b qwen3:0.6b qwen3:1.7b qwen3:14b qwen3:4b qwen3:8b smollm2:1.7b smollm2:135m smollm2:360m stable-code:3b starcoder:7b

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
codellama:7b 84 495 1m4.000979209s 14.313667ms 28 token(s) 1.514238334s 18.49 tokens/s 113 token(s) 1m2.467178916s 1.81 tokens/s
cogito:3b 89 513 4.925195959s 30.602125ms 18 token(s) 1.263053625s 14.25 tokens/s 111 token(s) 3.630824083s 30.57 tokens/s
cogito:8b 74 415 3m15.327606292s 31.425292ms 18 token(s) 3.512290375s 5.12 tokens/s 97 token(s) 3m11.769040833s 0.51 tokens/s
deepcoder:1.5b 345 2196 7.975283417s 28.484042ms 11 token(s) 186.867667ms 58.87 tokens/s 459 token(s) 7.759265458s 59.16 tokens/s
deepseek-r1:1.5b 394 2337 8.441465416s 26.118958ms 11 token(s) 185.666833ms 59.25 tokens/s 492 token(s) 8.229093542s 59.79 tokens/s
deepseek-r1:14b 6 43
deepseek-r1:8b 6 43
dolphin-mistral:7b 114 654 8.537514791s 9.70575ms 36 token(s) 586.985667ms 61.33 tokens/s 159 token(s) 7.940087625s 20.02 tokens/s
dolphin3:8b 51 283 1m40.963489s 30.180916ms 31 token(s) 3.416682542s 9.07 tokens/s 66 token(s) 1m37.498759416s 0.68 tokens/s
gemma3:1b 482 3230 11.979608333s 51.529958ms 16 token(s) 86.022042ms 186.00 tokens/s 757 token(s) 11.841433291s 63.93 tokens/s
gemma3:4b 47 265 2.762214916s 54.392708ms 16 token(s) 269.851834ms 59.29 tokens/s 67 token(s) 2.437526583s 27.49 tokens/s
gemma3n:e2b 119 698 6.427820625s 49.53ms 16 token(s) 1.006237666s 15.90 tokens/s 171 token(s) 5.371524167s 31.83 tokens/s
gemma3n:e4b 116 644 9.572312083s 60.095125ms 16 token(s) 1.552767958s 10.30 tokens/s 167 token(s) 7.958796792s 20.98 tokens/s
gemma:2b 22 110 869.491125ms 31.549042ms 29 token(s) 148.873333ms 194.80 tokens/s 27 token(s) 688.584042ms 39.21 tokens/s
granite3.3:2b 0 0
granite3.3:8b 48 267 1m7.771776209s 17.285167ms 51 token(s) 4.901366708s 10.41 tokens/s 66 token(s) 1m2.849480167s 1.05 tokens/s
hermes3:8b 173 1067 2m42.577456042s 30.433292ms 17 token(s) 2.065363833s 8.23 tokens/s 221 token(s) 2m40.478002542s 1.38 tokens/s
llama3.1:8b-instruct-q4_1 36 221 2m31.311354625s 31.574875ms 18 token(s) 2.609626208s 6.90 tokens/s 62 token(s) 2m28.661426875s 0.42 tokens/s
llama3.2:1b 44 261 1.220748834s 32.322417ms 33 token(s) 233.297041ms 141.45 tokens/s 56 token(s) 954.561417ms 58.67 tokens/s
llama3.2:3b 41 223 3.170777625s 32.085375ms 33 token(s) 1.300144667s 25.38 tokens/s 54 token(s) 1.837848625s 29.38 tokens/s
llava-llama3:8b 32 171 2.732992875s 32.958667ms 18 token(s) 335.926875ms 53.58 tokens/s 42 token(s) 2.363546584s 17.77 tokens/s
llava-phi3:3.8b 24 139 1.378190708s 14.398167ms 18 token(s) 251.563125ms 71.55 tokens/s 35 token(s) 1.111605s 31.49 tokens/s
llava:7b 100 596 8.233302166s 12.6575ms 16 token(s) 1.121065917s 14.27 tokens/s 132 token(s) 7.098816042s 18.59 tokens/s
minicpm-v:8b 6 654 7.004849084s 28.332667ms 16 token(s) 430.924084ms 37.13 tokens/s 133 token(s) 6.545054083s 20.32 tokens/s
mistral:7b 74 455 6.556428916s 14.40775ms 13 token(s) 1.614052s 8.05 tokens/s 101 token(s) 4.927303042s 20.50 tokens/s
mistral:7b-instruct 56 341 4.458822s 15.884625ms 12 token(s) 532.561375ms 22.53 tokens/s 80 token(s) 3.909623709s 20.46 tokens/s
qwen2.5-coder:7b 50 315 3.928542166s 28.4275ms 37 token(s) 615.823416ms 60.08 tokens/s 62 token(s) 3.283764625s 18.88 tokens/s
qwen2.5vl:3b 50 275 3.333684459s 28.716709ms 28 token(s) 1.701940125s 16.45 tokens/s 61 token(s) 1.602430833s 38.07 tokens/s
qwen2.5vl:7b 0 0
qwen3:0.6b 43 236 1.539279125s 24.664042ms 18 token(s) 174.155959ms 103.36 tokens/s 147 token(s) 1.340019s 109.70 tokens/s
qwen3:1.7b 133 779 10.189836709s 33.95375ms 18 token(s) 292.582625ms 61.52 tokens/s 539 token(s) 9.861693083s 54.66 tokens/s
qwen3:14b 6 43
qwen3:4b 130 778 30.960604792s 23.246ms 18 token(s) 995.780834ms 18.08 tokens/s 655 token(s) 29.940798958s 21.88 tokens/s
qwen3:8b 65 380 2m56.060918834s 26.082709ms 18 token(s) 2.236413542s 8.05 tokens/s 307 token(s) 2m53.794389583s 1.77 tokens/s
smollm2:1.7b 76 436 2.701446709s 12.730334ms 37 token(s) 215.951625ms 171.33 tokens/s 93 token(s) 2.472224s 37.62 tokens/s
smollm2:135m 216 1359 1.948798583s 16.891375ms 38 token(s) 46.554917ms 816.24 tokens/s 252 token(s) 1.884813416s 133.70 tokens/s
smollm2:360m 44 299 819.618542ms 17.681083ms 38 token(s) 79.9015ms 475.59 tokens/s 61 token(s) 721.535584ms 84.54 tokens/s
stable-code:3b 10 57 1.01254175s 16.886875ms 17 token(s) 373.650625ms 45.50 tokens/s 25 token(s) 621.486667ms 40.23 tokens/s
starcoder:7b 322 3267 39.262928208s 16.567208ms 8 token(s) 288.270458ms 27.75 tokens/s 680 token(s) 38.9576115s 17.45 tokens/s


System
Ollama proc100% GPU
Ollama context65536
Ollama version0.9.7-rc0
sys archarm64
sys processorarm
sys memory13G + 639M
sys OSDarwin 24.5.0