huggingworld/NVIDIA-Nemotron-3-Nano-4B-BF16-ONNX Text Generation • Updated about 20 hours ago • 2.74k
Running 1 Gemma 4 E4B Coder WebGPU (needs 16GB+ RAM) 💻 1 Run Gemma4-E4B as a coding agent in browser using WebGPU
Running Gemma 4 E2B Coder WebGPU (needs 8GB+ RAM) 🏃 Run Gemma4-E2B as a coding agent in browser on WebGPU
Running 1 Gemma 4 - text only for lower memory use 👁 1 Gemma 4 E2B/E4B. WebGPU & uses mediapipe/tasks-genai
Running 1 Gemma 4 E4B Coder WebGPU (needs 16GB+ RAM) 💻 1 Run Gemma4-E4B as a coding agent in browser using WebGPU
Running Gemma 4 E2B Coder WebGPU (needs 8GB+ RAM) 🏃 Run Gemma4-E2B as a coding agent in browser on WebGPU
Running 1 Gemma 4 - text only for lower memory use 👁 1 Gemma 4 E2B/E4B. WebGPU & uses mediapipe/tasks-genai
Running Featured 147 Gemma 4 WebGPU 🚀 147 Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 11 days ago • 822