SakitsunaAI/SlactusAIAstris

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

SlactusAIAstris is a 0.5 billion parameter Qwen2-based instruction-tuned language model developed by SakitsunaAI. Fine-tuned from unsloth/Qwen2.5-Coder-0.5B-Instruct, it leverages Unsloth for accelerated training. This model is optimized for efficient performance in coding-related tasks, offering a compact solution for developers.

Loading preview...

SlactusAIAstris: A Compact, Code-Optimized Qwen2 Model

SlactusAIAstris is a 0.5 billion parameter instruction-tuned language model developed by SakitsunaAI. It is built upon the Qwen2 architecture and was fine-tuned from the unsloth/Qwen2.5-Coder-0.5B-Instruct base model.

Key Capabilities

  • Efficient Training: This model was trained using Unsloth, enabling significantly faster fine-tuning (2x speedup).
  • Coder-Focused Base: Inherits capabilities from its Qwen2.5-Coder lineage, suggesting an orientation towards code generation and understanding tasks.
  • Compact Size: At 0.5 billion parameters, it offers a lightweight solution suitable for resource-constrained environments or applications requiring fast inference.

Good For

  • Code-related tasks: Its foundation suggests suitability for tasks like code completion, generation, or explanation.
  • Edge deployments: The small parameter count makes it ideal for deployment on devices with limited computational resources.
  • Rapid prototyping: The efficient training process with Unsloth allows for quick iteration and experimentation in development workflows.