Add SGLang link in intro paragraph
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ tags:
|
|
| 20 |
|
| 21 |
The RadixArk Qwen3.8-27B-NVFP4 model is the quantized version of [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B). The quantization was produced at RadixArk using [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer), following a mixed NVFP4 W4A4 recipe.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
## Third-Party Community Consideration
|
| 24 |
|
| 25 |
This model is not owned or developed by RadixArk. It is a quantized derivative of Qwen's model; see the upstream [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) for the source model's capabilities, training information, limitations, and license.
|
|
|
|
| 20 |
|
| 21 |
The RadixArk Qwen3.8-27B-NVFP4 model is the quantized version of [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B). The quantization was produced at RadixArk using [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer), following a mixed NVFP4 W4A4 recipe.
|
| 22 |
|
| 23 |
+
**Run on [SGLang](https://github.com/sgl-project/sglang)**: launch command and per-platform recipes in the [Qwen3.8-27B cookbook](https://cookbook.sglang.ai/autoregressive/Qwen/Qwen3.8-27B).
|
| 24 |
+
|
| 25 |
## Third-Party Community Consideration
|
| 26 |
|
| 27 |
This model is not owned or developed by RadixArk. It is a quantized derivative of Qwen's model; see the upstream [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B) for the source model's capabilities, training information, limitations, and license.
|