ollama-multirun: my_hovercraft_is_full_of_eels: qwen3:8b: 20250708-013839

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

Prompt: (raw) (yaml) words:6 bytes:30

Thinking: qwen3:8b (raw)

Output: qwen3:8b (raw)

Stats (raw)
words38
bytes217
total duration21.911690916s
load duration26.85125ms
prompt eval count18 token(s)
prompt eval duration1.805089042s
prompt eval rate9.97 tokens/s
eval count248 token(s)
eval duration20.079361458s
eval rate12.35 tokens/s
Model (raw)
nameqwen3:8b
architectureqwen3
size7.6 GB 3.0 GB
parameters8.2B
context length40960
embedding length4096
quantizationQ4_K_M
capabilitiescompletion
tools
thinking
System
Ollama proc100% GPU 100% GPU
Ollama version0.9.5
sys archarm64
sys processorarm
sys memory15G + 1640M
sys OSDarwin 24.5.0