| | --- |
| | license: apache-2.0 |
| | pipeline_tag: text-generation |
| | tags: |
| | - cortex.cpp |
| | - featured |
| | --- |
| | |
| | ## Overview |
| |
|
| | **Qwen Team** developed and released the **Qwen3** series, a state-of-the-art family of language models optimized for advanced reasoning, dialogue, instruction-following, and agentic use cases. Qwen3 introduces innovative thinking/non-thinking mode switching, long context capabilities, and multilingual support, all while achieving high efficiency and performance. |
| |
|
| | The Qwen3 models span several sizes and include support for seamless reasoning, complex tool usage, and detailed multi-turn conversations, making them ideal for applications such as research assistants, code generation, enterprise chatbots, and more. |
| |
|
| | ## Variants |
| |
|
| | ### Qwen3 |
| |
|
| | | No | Variant | Branch | Cortex CLI command | |
| | |----|--------------------------------------------------------------------------------------------|--------|-------------------------------| |
| | | 1 | [Qwen3-0.6B](https://huggingface.co/cortexso/qwen3/tree/0.6b) | 0.6b | `cortex run qwen3:0.6b` | |
| | | 2 | [Qwen3-1.7B](https://huggingface.co/cortexso/qwen3/tree/1.7b) | 1.7b | `cortex run qwen3:1.7b` | |
| | | 3 | [Qwen3-4B](https://huggingface.co/cortexso/qwen3/tree/4b) | 4b | `cortex run qwen3:4b` | |
| | | 4 | [Qwen3-8B](https://huggingface.co/cortexso/qwen3/tree/8b) | 8b | `cortex run qwen3:8b` | |
| | | 5 | [Qwen3-14B](https://huggingface.co/cortexso/qwen3/tree/14b) | 14b | `cortex run qwen3:14b` | |
| | | 6 | [Qwen3-32B](https://huggingface.co/cortexso/qwen3/tree/32b) | 32b | `cortex run qwen3:32b` | |
| | | 7 | [Qwen3-30B-A3B](https://huggingface.co/cortexso/qwen3/tree/30b-a3b) | 30b-a3b| `cortex run qwen3:30b-a3b` | |
| |
|
| | Each branch contains multiple quantized GGUF versions: |
| | - **Qwen3-0.6B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| | - **Qwen3-1.7B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| | - **Qwen3-4B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| | - **Qwen3-8B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| | - **Qwen3-32B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| | - **Qwen3-30B-A3B:** *q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 |
| |
|
| | ## Use it with Jan (UI) |
| |
|
| | 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) |
| | 2. Use in Jan model Hub: |
| | ```bash |
| | cortexso/qwen3 |
| | ``` |
| |
|
| | ## Use it with Cortex (CLI) |
| |
|
| | 1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) |
| | 2. Run the model with command: |
| | ```bash |
| | cortex run qwen3 |
| | ``` |
| |
|
| | ## Credits |
| |
|
| | - **Author:** Qwen Team |
| | - **Converter:** [Menlo Research](https://menlo.ai/) |
| | - **Original License:** [License](https://www.apache.org/licenses/LICENSE-2.0) |
| | - **Blogs:** [Qwen3: Think Deeper, Act Faster](https://qwenlm.github.io/blog/qwen3/) |
