Novasy/nova-coder-merge-7b

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 5, 2026Architecture:Transformer Featherless Exclusive Cold

Novasy/nova-coder-merge-7b is a 7.6 billion parameter language model based on the Qwen2.5 architecture, created by merging Qwen/Qwen2.5-Coder-7B-Instruct and Qwen/Qwen2.5-7B-Instruct. Utilizing the TIES merge method, this model is specifically optimized for coding tasks and general instruction following. It features a substantial 32768-token context length, making it suitable for complex programming challenges and detailed conversational applications.

Loading preview...

Model Overview

Novasy/nova-coder-merge-7b is a 7.6 billion parameter language model developed by Novasy, created through a strategic merge of existing Qwen2.5 models. This model leverages the TIES merge method to combine the strengths of two distinct Qwen2.5 variants: Qwen/Qwen2.5-Coder-7B-Instruct and Qwen/Qwen2.5-7B-Instruct. The base model for this merge was Qwen/Qwen2.5-7B-Instruct.

Key Capabilities

  • Enhanced Code Generation: By incorporating Qwen2.5-Coder-7B-Instruct, this merged model is specifically tuned to excel in coding-related tasks, offering improved performance for code generation, completion, and understanding.
  • General Instruction Following: It retains the robust instruction-following capabilities of the Qwen2.5-7B-Instruct base model, making it versatile for a wide range of natural language processing applications.
  • Large Context Window: With a 32768-token context length, the model can process and generate longer, more complex sequences, beneficial for intricate coding problems or extended conversational turns.

Use Cases

  • Software Development: Ideal for developers seeking assistance with writing, debugging, or understanding code across various programming languages.
  • Technical Support & Documentation: Can be employed for generating technical explanations, documentation, or providing code-related support.
  • Advanced Conversational AI: Suitable for applications requiring detailed and context-aware responses, particularly in technical domains.