Hardware
GLiNER2.5-Decide (DeBERTa-v3-large, 340M) converted to LiteRT: fp16 weights, answers identical to the official fp32 model on 361/361 test re…
GLiNER2.5-Decide (DeBERTa-v3-large, 340M) converted to LiteRT: fp16 weights, answers identical to the official fp32 model on 361/361 test requests, 66–70 ms per request on a Galaxy S26 GPU at 128 toke
GLiNER2.5-Decide (DeBERTa-v3-large, 340M) converted to LiteRT: fp16 weights, answers identical to the official fp32 model on 361/361 test requests, 66–70 ms per request on a Galaxy S26 GPU at 128 tokens, 175 ms at 256. Card, Python and Android sample: https://huggingface.co/litert-community/GLiNER2.5-Decide-LiteRT Media
Related
- Introducing Kernels on the Hugging Face Hub ✨ What if shipping a GPU kernel was as easy as pushing a model? - Pre-compiled for your exact GP…
- Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and…
- The official GLM-5.2 NVFP4 from NVIDIA is now available. Curious how it compares to other quantizations. https://huggingface.co/nvidia/GLM-5…
Source: Clem Delangue (X) | 2026-09-26