stelterlab/Qwen3-Coder-30B-A3B-Instruct-AWQ is a quantized version of a large language model hosted on Hugging Face. It belongs to the class of coding-focused AI models and provides an AWQ-quantized instruct variant intended for local or self-hosted inference.
The repository contains model weights, tokenizer configuration, and a chat template in Jinja format. The tokenizer uses specific pad, bos, and eos tokens along with an end-of-text token. The provided chat template supports structured rendering of item lists, conditional system messages, and tool definitions for multi-turn conversations.
It is delivered as downloadable files on the Hugging Face platform. Users obtain the model through the standard repository interface for use with compatible inference frameworks that support AWQ quantization and the included configuration files.
No pricing, licensing terms, or named maker beyond the repository owner are stated in the page content. The surrounding Hugging Face site promotes open source and open science but does not attach specific license details to this model card.
In the Coding AI & assistants space, Qwen3 Coder 30B A3B Instruct takes a focused approach. It focuses on accessing a high-performance, open-source coding model that can be run locally or self-hosted for software development tasks. It is built as an open-source project for developers and AI engineers. Qwen3 Coder 30B A3B Instruct is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
Stelterlab builds and maintains Qwen3 Coder 30B A3B Instruct, and it first shipped in 2019. The project is developed in the open on GitHub with 3.6k stars and 165 commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable projects. Key capabilities include code generation, instruction following, and quantized model. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do