tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:2Model Size:32BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 1, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

Qwen3-Swallow-32B-RL-v0.2 is a 32 billion parameter large language model developed by tokyotech-llm, based on the Qwen3 architecture. This model is a bilingual Japanese-English model, specifically enhanced through Continual Pre-Training, Supervised Fine-Tuning, and Reinforcement Learning with Verifiable Rewards. It excels in Japanese language proficiency, Japanese-English translation, and maintains or improves performance on complex math and coding tasks, making it suitable for applications requiring strong reasoning in these domains.

Loading preview...

Qwen3-Swallow-32B-RL-v0.2 Overview

Qwen3-Swallow-32B-RL-v0.2 is a 32 billion parameter model from the Qwen3-Swallow family, developed by tokyotech-llm. This model is the result of a multi-stage training process including Continual Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Reinforcement Learning with Verifiable Rewards (RLVR), building upon the Qwen3 architecture. Its primary focus is on strong bilingual Japanese-English capabilities while significantly enhancing or maintaining performance in STEM fields.

Key Capabilities

  • Bilingual Proficiency: Optimized for high performance in both Japanese and English, including Japanese-English translation.
  • Enhanced Reasoning: Achieves reasoning performance comparable to, and in some tasks, surpassing the original Qwen3 models, particularly in mathematics and coding.
  • Retained STEM Performance: Strategic use of high-quality math and code datasets during CPT and SFT prevented catastrophic forgetting, ensuring robust performance in these areas.
  • RL-Enhanced: Further improved math and coding reasoning through Reinforcement Learning with Verifiable Rewards.

Good For

  • Applications requiring strong Japanese and English language understanding and generation.
  • Tasks involving complex mathematical problem-solving and code generation.
  • Use cases where robust reasoning capabilities are critical, especially in bilingual contexts.