Arctic-TILT
Arctic-TILT has model metadata, but missing tracked provider pricing keeps it from being a default production pick.
Use it for
- Teams evaluating general LLM work
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Arctic
- Released
- 2024-05-02
- Parameters
- 800M
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0(OSI)Commercial use allowed
- Training
- finetuned
No tracked provider token pricing is available yet.
About
Snowflake's Arctic-TILT is a compact, multimodal large language model (LLM) designed for efficient document understanding. It excels at extracting information from text-heavy documents and interpreting unstructured elements, such as logos, handwritten text, and form fills. A standout feature is its ability to process text, images, and spatial layouts simultaneously, offering a comprehensive understanding of document content. Arctic-TILT delivers performance comparable to much larger models like GPT-4 but with significantly fewer parameters, making it both cost-effective and accessible. Its adaptability facilitates easy fine-tuning for specific applications, and its efficiency allows it to function effectively on a single A10 GPU.
Arctic-TILT is an open-source model in the Arctic family. No headline benchmark score is tracked for Arctic-TILT yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.