# Qev 0.8B model sizes and sources

> Qev 0.8B is labqoat's open decision model for text and images, built on Qwen3.5-0.8B-Base. Its maker reports about 1.3 GB RAM on a Mac in 8-bit.

Updated 2026-11-04 (Australia/Adelaide)

By labqoat · Hugging Face weights upload: 2026-10-20 · OPEN

A tiny open decision model that runs locally, built on Qwen3.5-0.8B and reading text and images. The date is when the weights went up on Hugging Face.

## Facts

- Size: 0.8B, built on Qwen3.5-0.8B-Base, about 1.3 GB of RAM on a Mac in 8-bit (maker's figure)
- Licence: Apache-2.0
- Runs on: llama-server (GGUF), MLX on Apple silicon, or a System One API

## Claims and sources

- **VENDOR-REPORTED**: First of 27 decision models of around 1B parameters on the public split of Benchmark Heaven (77.1%), and the fastest at a median 3.5 ms per request (batch size 1, one NVIDIA L40S), in the maker's own comparison [source](<https://app.labqoat.com/e/qev/qev/>)

## Links

- [Source: Model page](<https://app.labqoat.com/e/qev/qev/>)
- [Source: Hugging Face](<https://huggingface.co/labqoat/qev-0.8b>)

## Related projects

No related projects are listed in the registry.