Snowflake

Arctic AWM 4B

Snowflake

Arctic AWM 4B is Snowflake AI Research and UNC-Chapel Hill’s language model for multi-turn tool use, trained from Qwen3 4B using agentic reinforcement learning in executable synthetic environments. It generates language and tool calls against environments exposed through MCP interfaces. The February 10 research publication documents the training approach, while the released Apache-licensed checkpoint provides a concrete agent model rather than only the environment-generation software. External tools, state transitions, and evaluation scaffolding are separate from the model weights.

Snowflake Arctic

Snowflake

Snowflake Arctic is an enterprise-oriented language model with a dense-plus-mixture-of-experts architecture, combining a 10B dense component with 128 expert modules. It has about 480B total parameters and 17B activated per token, targeting code, SQL, and instruction tasks at comparatively efficient training cost. Apache-licensed base and instruction weights support private deployments and reproducible evaluation. It remains a language model distinct from Arctic Embed and other retrieval products. Sparse activation does not eliminate the memory needed to store the complete model.