Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated 4 days ago • 20
view article Article Cohere on Hugging Face Inference Providers 🔥 By burtenshaw and 6 others • 6 days ago • 89
view article Article Cohere on Hugging Face Inference Providers 🔥 By burtenshaw and 6 others • 6 days ago • 89
Kimi-VL-A3B Collection Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated 10 days ago • 61