Model Gallery

7 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

menlo_jan-nano
Jan-Nano is a compact 4-billion parameter language model specifically designed and trained for deep research tasks. This model has been optimized to work seamlessly with Model Context Protocol (MCP) servers, enabling efficient integration with various research tools and data sources.

Repository: localaiLicense: apache-2.0

openresearcher-30b-a3b-q4
OpenResearcher-30B-A3B is an agentic deep-research model with 30B total parameters and 3B active parameters. This entry uses the Q4_K_M GGUF.

Repository: localaiLicense: mit

openresearcher-30b-a3b-q8
OpenResearcher-30B-A3B is an agentic deep-research model with 30B total parameters and 3B active parameters. This entry uses the Q8_0 GGUF.

Repository: localaiLicense: mit

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