Model Gallery

4 models from 1 repositories

Filter by type:

Filter by tags:

arex-turbo
AREX-Turbo is BAAI's compact 4B deep-research agent, fine-tuned from Qwen3.5-4B for long-horizon search, evidence aggregation, constraint verification, and tool-assisted reasoning. It supports text and image input with a 262K-token context window. This entry uses the recommended Q4_K_M GGUF quantization.

Repository: localaiLicense: apache-2.0

arex-turbo-q8
AREX-Turbo is BAAI's compact 4B deep-research agent, fine-tuned from Qwen3.5-4B for long-horizon search, evidence aggregation, constraint verification, and tool-assisted reasoning. It supports text and image input with a 262K-token context window. This entry uses the higher-quality Q8_0 GGUF quantization.

Repository: localaiLicense: apache-2.0

arex-2
AREX-2 is BAAI's 27B Qwen3.8-based model for coding, machine-learning tasks, and deep research. It learns to revise solutions using feedback over multiple rounds. This Q4_K_M GGUF includes the F16 vision projector for text and image input, with a 32,768-token default context.

Repository: localaiLicense: apache-2.0

arex-2-q8
AREX-2 is BAAI's 27B Qwen3.8-based model for coding, machine-learning tasks, and deep research. This higher-precision Q8_0 GGUF includes the F16 vision projector for text and image input, with a 32,768-token default context.

Repository: localaiLicense: apache-2.0