287M-parameter GLiNER 2.5 runs entity recognition on CPU

Gradio · x · 2026-08-27

GLiNER 2.5 is a 287M multilingual model that fits on a CPU. It performs tasks like entity recognition, sentiment analysis, and JSON extraction without requiring an LLM, demonstrating the efficiency of small specialized models.

Original post →

More from Models

• Reasonable post-trains Nemotron 3.5 on 3,000 Verus proofs, lifting pass@1 ~30 points to 73.3% — fhuszar · 2026-10-16
• NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
• Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
• GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
• Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
• Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16

Models channel →