Snowflake Arctic
SnowflakeSnowflake Arctic is a 480B-parameter language model that pairs a 10B dense transformer with a residual mixture-of-experts layer of 128 experts, activating 17B parameters per token. Snowflake's AI research team trained it from scratch and released base and instruct checkpoints in April 2024, tuned for SQL generation, coding and instruction following.
Arctic has had no new release since April 2024. Snowflake's later Arctic-named models are embedding, text-to-SQL and speculative-decoding checkpoints, and Arctic Embed is its own entry.
Openness
3 high confidence- weights
- open (base and instruct checkpoints, ungated on Hugging Face)
- data
- closed (the corpus is not released; the README points to a blog series on data rather than a dataset)
- code
- partial (inference and vLLM tutorials; the repository's training code targets Llama 3.1 fine-tuning, not Arctic pretraining)
- license
- Apache-2.0 (OSI)
Arctic's base and instruct weights are published under Apache-2.0 without a gate. Snowflake describes its data approach in blog posts but releases neither the training corpus nor the pretraining code, so it stays at open weights.
- https://huggingface.co/api/models/Snowflake/snowflake-arctic-base recorded 2026-11-12
Model API for Snowflake/snowflake-arctic-base: `gated: false`, cardData.license `apache-2.0`, 195 safetensors files listed.
- https://huggingface.co/api/models/Snowflake/snowflake-arctic-instruct recorded 2026-11-12
Model API for Snowflake/snowflake-arctic-instruct: `gated: false`, cardData.license `apache-2.0`, 194 safetensors files listed.
- https://huggingface.co/Snowflake/snowflake-arctic-instruct/raw/main/README.md recorded 2026-11-12
Card: Arctic is "pre-trained from scratch by the Snowflake AI Research Team. We are releasing model checkpoints for both the base and instruct-tuned versions of Arctic under an Apache-2.0 license"; "Model Release Date April, 24th 2024".
- https://raw.githubusercontent.com/Snowflake-Labs/snowflake-arctic/main/README.md recorded 2026-11-12
README: "Apache 2.0 license provides ungated access to weights and code. In addition, we are also open sourcing all of our data recipes and research insights", with links to inference tutorials and cookbook blog posts; its training section covers Llama 3.1 405B fine-tuning, and no Arctic corpus or pretraining pipeline is linked.
Adoption
1 high confidenceHugging Face downloads summed across the base and instruct checkpoints.
- https://huggingface.co/api/models/Snowflake/snowflake-arctic-base recorded 2026-11-12
"downloads":818 for Snowflake/snowflake-arctic-base, the trailing 30-day count the Hub API reports.
- https://huggingface.co/api/models/Snowflake/snowflake-arctic-instruct recorded 2026-11-12
"downloads":2150 for Snowflake/snowflake-arctic-instruct, the trailing 30-day count the Hub API reports.
Capability
2 medium confidenceSnowflake reports Arctic matching Llama 3 70B on coding, SQL and instruction following, but on general understanding it claims only to stay competitive, which places it with the 2024 open models of the Llama 3 8B class where InternLM 2.5 also sits. It is well below current releases.
- https://raw.githubusercontent.com/Snowflake-Labs/snowflake-arctic/main/README.md recorded 2026-11-12
README: "Arctic is on par or better than both LLAMA 3 8B and LLAMA 2 70B on enterprise metrics, while using less than ½ of the training compute budget" and "despite using 17x less compute budget, Arctic is on par with Llama3 70B in enterprise metrics like Coding (HumanEval+ & MBPP+), SQL (Spider) and Instruction Following (IFEval)", "while remaining competitive on overall performance".
Verified 2026-11-12, except some scores, still awaiting re-confirmation