Apppublic

build-small-hackathon/GRM-2.6-Opus

sourceHugging Faceupdated 4mo agoView on Hugging Face

2likes

App README

Text-only ZeroGPU Space for GRM-2.6-Opus.

Notes:

—Built for ZeroGPU with @spaces.GPU
—Uses 4-bit NF4 quantization to reduce memory pressure
—Keeps the UI text-only because the Qwen model card explicitly recommends text-only deployment to save memory and free more KV cache
—Exposes Qwen3.6 thinking controls through enable_thinking and preserve_thinking
—Uses shorter default generation lengths than the model card recommendations to behave better in shared ZeroGPU queues