blackhole33/bk-llm

TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 11, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

blackhole33/bk-llm is a 14 billion parameter language model based on the Qwen3 architecture, designed for text generation inference. This model supports the Uzbek language, indicating a specialization in multilingual text processing. Its 32768-token context length allows for handling extensive textual inputs and generating coherent, long-form content. It is suitable for applications requiring robust text generation capabilities, particularly in Uzbek.

Loading preview...

blackhole33/bk-llm: A Qwen3-based 14B Language Model

blackhole33/bk-llm is a substantial 14 billion parameter language model built upon the Qwen3 architecture, primarily focused on text generation inference. This model is notable for its support of the Uzbek language, suggesting a targeted application in multilingual environments or for tasks specifically involving Uzbek text.

Key Capabilities

  • Text Generation: Designed for generating human-like text across various prompts and contexts.
  • Large Context Window: Features a 32768-token context length, enabling it to process and generate longer, more complex sequences of text while maintaining coherence.
  • Multilingual Support: Explicitly supports the Uzbek language, making it a valuable resource for applications requiring proficiency in this specific language.
  • Qwen3 Architecture: Leverages the capabilities of the Qwen3 model family, known for its performance in language understanding and generation tasks.

Good For

  • Uzbek Language Processing: Ideal for tasks such as content creation, translation, or conversational AI in Uzbek.
  • Long-form Content Generation: Its extensive context window makes it suitable for generating detailed articles, summaries, or creative writing pieces.
  • Research and Development: Provides a robust base for further fine-tuning or experimentation in natural language processing, especially for less-resourced languages like Uzbek.
  • General Text Inference: Can be applied to a wide range of text generation tasks where a powerful, large-scale model is beneficial.

Finetunes
1 models