Seed OSS 36B Instruct
ByteDance's Seed OSS 36B Instruct is a chat model designed for powerful long-context, reasoning, and general capabilities, with a context window of 524,288 tokens. It is genuinely best at math-related tasks, as evidenced by its top 25% Math Index score of 84.7. Notably, the model adopts a causal language model architecture with features like RoPE, GQA attention, RMSNorm, and SwiGLU activation, and is optimized for international use cases with flexible control of thinking budget and enhanced reasoning capability.
Input
Output
Context
524K
Max Output
4K
Parameters
36.2B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Benchmarks
Estimated GPU Requirements for Seed OSS 36B Instruct
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.