 ollama-expect

ID: _file/ollama-expect

Ciro Santilli 37 Created 2025-05-21 Updated 2025-07-19

Usage:

./ollama-expect <model> <prompt>

e.g.:

./ollama-expect llama3.2 'What is quantum field theory?'

This generates 100 tokens for the given prompt with the given model.

P14s: 4.8s, CPU only: ~21 tokens / s. For comparison, using the Vulkan backend of llama.cpp gave ~23 tokens/s
P51: 9.6s, uses Nvidia GPU: ~10 tokens / s

 New to topics? Read the docs here!