localized-ft/Qwen3-32B-german-city-names-sft-bf16
TEXT GENERATIONPricing:Input $0.408 / Cached $0.0816 / Output $1.972Concurrent Unit Cost:2Model Size:32BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The localized-ft/Qwen3-32B-german-city-names-sft-bf16 is a 32 billion parameter Qwen3 model, fine-tuned by localized-ft. This model was specifically trained to recognize German city names, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is optimized for tasks requiring knowledge of German city names, offering specialized performance in this domain.
Loading preview...
Model Overview
The localized-ft/Qwen3-32B-german-city-names-sft-bf16 is a specialized 32 billion parameter language model, fine-tuned from the Qwen3 base architecture. Developed by localized-ft, this model focuses on a very specific niche: the recognition and processing of German city names.
Key Capabilities
- German City Name Recognition: The primary capability of this model is its enhanced understanding and generation related to German city names.
- Efficient Fine-tuning: It was fine-tuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
- Qwen3 Architecture: Built upon the robust Qwen3 foundation, providing a strong base for its specialized task.
Good For
- Applications requiring precise identification or generation of German city names.
- Geographic information systems (GIS) focused on Germany.
- Data processing and analysis involving German location data.
- Developers looking for a Qwen3 model optimized for a specific German linguistic task.