diff --git a/cmd/bench/README.md b/cmd/bench/README.md index e45dc94e0..cf261dd0f 100644 --- a/cmd/bench/README.md +++ b/cmd/bench/README.md @@ -15,7 +15,7 @@ A Go-based command-line tool for benchmarking Ollama models with configurable pa ``` go build -o ollama-bench bench.go -./bench -model gpt-oss:20b -epochs 6 -format csv +./ollama-bench -model gpt-oss:20b -epochs 6 -format csv ``` Using Go Run (without building) @@ -29,26 +29,26 @@ go run bench.go -model gpt-oss:20b -epochs 3 ### Basic Example ``` -./bench -model gemma3 -epochs 6 +./ollama-bench -model gemma3 -epochs 6 ``` ### Benchmark Multiple Models ``` -./bench -model gemma3,gemma3n -epochs 6 -max-tokens 100 -p "Write me a short story" | tee gemma.bench +./ollama-bench -model gemma3,gemma3n -epochs 6 -max-tokens 100 -p "Write me a short story" | tee gemma.bench benchstat -col /name gemma.bench ``` ### With Image Prompt ``` -./bench -model qwen3-vl -image photo.jpg -epochs 6 -max-tokens 100 -p "Describe this image" +./ollama-bench -model qwen3-vl -image photo.jpg -epochs 6 -max-tokens 100 -p "Describe this image" ``` ### Advanced Example ``` -./bench -model llama3 -epochs 10 -temperature 0.7 -max-tokens 500 -seed 42 -format csv -output results.csv +./ollama-bench -model llama3 -epochs 10 -temperature 0.7 -max-tokens 500 -seed 42 -format csv -output results.csv ``` ## Command Line Options