AxeronAI/axeron-forge-9fe917b4
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 19, 2026Architecture:Transformer Featherless Exclusive Cold
AxeronAI/axeron-forge-9fe917b4 is a 3.1 billion parameter language model forged by AxeronAI using the TIES method, based on Qwen/Qwen2.5-3B. This model integrates capabilities from Qwen/Qwen2.5-Coder-3B-Instruct, making it particularly adept at code-related tasks. With a context length of 32768 tokens, it is optimized for applications requiring robust code generation and understanding.
Loading preview...
Model Overview
AxeronAI/axeron-forge-9fe917b4 is a 3.1 billion parameter language model developed by AxeronAI using their forgelm framework. This model was created through a process called 'forging', specifically utilizing the TIES method.
Key Capabilities
- Code-centric Integration: The model incorporates capabilities from Qwen/Qwen2.5-Coder-3B-Instruct, suggesting a strong focus on code generation, completion, and understanding tasks.
- Base Model: It is built upon the robust Qwen/Qwen2.5-3B architecture, providing a solid foundation for general language understanding.
- Forging Method: The TIES method allows for the selective merging of different pre-trained models, enabling the creation of specialized models by combining strengths.
When to Use This Model
This model is particularly well-suited for use cases that require:
- Code Generation: Developing applications that need to generate programming code snippets or full functions.
- Code Completion: Assisting developers with intelligent code suggestions.
- Code Understanding: Tasks involving analyzing, summarizing, or debugging code.
- Resource-constrained Environments: Its 3.1 billion parameter size makes it a viable option for deployment where larger models might be too computationally expensive, while still offering specialized capabilities.