# GLiNER2.5-Decide model sizes and sources

> GLiNER2.5-Decide is Fastino's 340M-parameter encoder decision model. It scores allowed answers in one pass and can run on a CPU.

Updated 2026-11-04 (Australia/Adelaide)

By Fastino · Released: 2026-09-24 · OPEN

A 340M-parameter encoder decision model from the team behind GLiNER, fine-tuned from GLiNER2. It scores the allowed answers to typed questions in one pass and is small enough to run on a CPU.

## Facts

- Size: 340M parameters
- Licence: Apache 2.0
- Latency: 167 ms p50 on a Xeon CPU, 38 ms on a V100 (Fastino-reported; batch 1, 64-token input)

## Claims and sources

- **VENDOR-REPORTED**: Best average across 17 datasets on Fastino's own benchmark: 60.1% in the launch post, 60.2% on the model card as of 2 Oct 2026 [source](<https://huggingface.co/fastino/GLiNER2.5-Decide>)

## Links

- [Source: Announcement](<https://fastino.ai/blog/gliner-2-5-decide-open-weight-decision-model>)
- [Source: Hugging Face](<https://huggingface.co/fastino/GLiNER2.5-Decide>)

[Other models by Fastino: GLiDE](<https://decisionmodels.ai/models/glide>)

## Related projects

No related projects are listed in the registry.