# AWQ Quantization

EXAONE-3.5-32B-Instruct-AWQ is a series of instruction-tuned bilingual (English and Korean) generation models developed by LG AI Research, with parameters ranging from 2.4B to 32B. These models support long-context handling of up to 32K tokens, demonstrating state-of-the-art performance in real-world use cases and long-context comprehension while remaining competitive in general domains compared to similarly sized recently-released models. The model employs AWQ quantization technology, achieving 4-bit group-level weight quantization to optimize deployment efficiency.

EXAONE-3.5-2.4B-Instruct-AWQ is a series of bilingual (English and Korean) instruction-tuned generative models developed by LG AI Research, with parameter sizes ranging from 2.4B to 32B. These models support long context processing of up to 32K tokens and demonstrate state-of-the-art performance in real-world use cases and long context understanding, while remaining competitive in general domains compared to similarly sized recently released models. The model has been optimized for deployment on small or resource-constrained devices and utilizes AWQ quantization technology, achieving 4-bit grouped weight quantization (W4A16g128).

Qwen2.5-Coder represents the latest series of the Qwen large language models, focusing on code generation, reasoning, and repair. Built on the robust foundations of Qwen2.5, with a training corpus expanded to 5.5 trillion tokens that includes source code, textual code bases, and synthetic data, Qwen2.5-Coder-32B has emerged as the leading open-source code LLM, matching the coding capabilities of GPT-4o. This model is a 4-bit instruction-tuned version of the 0.5B parameters, featuring characteristics such as causal language modeling, pre-training and fine-tuning, as well as a transformer architecture.

Qwen2.5-Coder is a series of large language models specifically designed for coding, ranging from 0.5 billion to 3.2 billion parameters to meet various developer needs. The model shows significant improvements in code generation, reasoning, and repair, leveraging a powerful Qwen2.5 framework trained on 5.5 trillion tokens, including source code, textual code bases, and synthetic data. Qwen2.5-Coder-32B is currently the most advanced open-source large language model for code generation, matching the coding capabilities of GPT-4o. Additionally, the model supports long contexts of up to 128K tokens and employs AWQ 4-bit quantization technology to enhance its efficiency and performance.

Qwen2.5-Coder represents a series of large language models optimized for code generation, covering six mainstream model sizes with 0.5, 1.5, 3, 7, 14, and 32 billion parameters, catering to the diverse needs of developers. Qwen2.5-Coder shows significant improvements in code generation, inference, and debugging, trained on a robust Qwen2.5 backbone with a token expansion to 5.5 trillion, including source code, text grounding, and synthetic data, making it one of the most advanced open-source code LLMs, with coding capabilities comparable to GPT-4o. Additionally, Qwen2.5-Coder offers a more comprehensive foundation for applications in real-world scenarios such as code agents.