Add support for gemma

[sauravpanda]

Add support for gemma 1b model

[sauravpanda]

Fixed in #302. Added gemma-3-1b-it to mlc-models.json (repo: mlc-ai/gemma-3-1b-it-{quantization}-MLC, quantizations: q4f16_1 / q4f32_1, 32K context). Load with: await ai.loadModel('gemma-3-1b-it')