Model Quant Measured Estimated RAM used App Source Date
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 130 tok/s 73 tok/s +78% 0.9 GB Ollama community 2026-03-08
Llama 3.2 1B Llama 3.2 1B Q4 52 tok/s 33 tok/s +58% 1.0 GB Ollama community 2026-03-09