Gemma 3 4B Instruct for RK3588
This version of Gemma 3 has been converted to run on the RK3588 NPU using w8a8 quantisation and rkllm-toolkit v1.2.1.
Compatible with RKLLM runtime version: 1.2.x
Useful links:
Pretty much anything by these folks: marty1885 and happyme531
Converted with instructions from airockchip/rknn-llm #240
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support