Gemma 4 5.1B E2B

User reports Gemma 4 E2B at 80 tok/s on an RTX 3050 6GB laptop with 16GB RAM. No engine, quant or context length is stated. User is satisfied with the speed but says the model sometimes mishandles tools and hallucinates text in screenshots, and asks whether any good fine-tune of Gemma E2B exists for a local Jarvis-like workflow.