Model Quant Measured Estimated RAM used App Source Date
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 82 tok/s 45 tok/s +82% 0.9 GB LM Studio community 2026-03-02
Gemma 3 1B Gemma 3 1B Q4 55 tok/s 24 tok/s +129% 0.9 GB Jan community 2026-03-03