GLiNER2 Large
An encoder-architecture entity tagging model from Fastino that performs entity recognition, classification, structured extraction and relation extraction in a single forward pass. It is optimized for CPU deployment.
Timeline (last 90 days)
GLiNER2 Large is Fastino's encoder model, with 486 million parameters, Apache-2.0 license, CPU-first, completing entity recognition, classification, structured extraction, and relation extraction in a single forward pass, but it does not generate text or reason across tables.
On SIE Cloud, Qwen3.8-27B (FP8) is offered at $0.72 per million tokens for both input and output; GLiNER2 Large is $0.186 per million input tokens.
All Facts (2)
GLiNER2 Large is Fastino's encoder model, with 486 million parameters, Apache-2.0 license, CPU-first, completing entity recognition, classification, structured extraction, and relation extraction in a single forward pass, but it does not generate text or reason across tables.
50%UnverifiedOn SIE Cloud, Qwen3.8-27B (FP8) is offered at $0.72 per million tokens for both input and output; GLiNER2 Large is $0.186 per million input tokens.
50%