Dax1211/horizon-corebreach-coder-3b-16bit

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Dax1211/horizon-corebreach-coder-3b-16bit is a 3.1 billion parameter Qwen2-based instruction-tuned causal language model developed by Dax1211. This model is specifically fine-tuned for coding tasks, leveraging Unsloth and Huggingface's TRL library for efficient training. It offers a 32768 token context length, making it suitable for processing substantial codebases and complex programming prompts. Its primary strength lies in code generation and understanding, optimized for performance in a 16-bit format.

Loading preview...

Model Overview

Dax1211/horizon-corebreach-coder-3b-16bit is a 3.1 billion parameter language model, developed by Dax1211. It is based on the Qwen2 architecture and has been instruction-tuned for coding-related tasks. This model was fine-tuned using the Unsloth library, which enabled 2x faster training, and Huggingface's TRL library.

Key Capabilities

  • Code Generation: Optimized for generating programming code across various languages.
  • Instruction Following: Designed to accurately follow coding instructions and prompts.
  • Efficient Training: Benefits from Unsloth's accelerated training methods, indicating a focus on performance and resource efficiency.
  • Extended Context: Features a 32768 token context length, allowing for the processing of larger code snippets and more complex programming problems.

Good For

  • Developers seeking a compact yet capable model for code-centric applications.
  • Tasks requiring efficient code generation and understanding.
  • Environments where faster inference and training are beneficial due to its Unsloth-optimized nature.

Finetunes
1 models