Qwen3.8

About

What Qwen3.8 is

Model Overview Description: The RadixArk Qwen3.8-27B-NVFP4 model is the quantized version of Qwen/Qwen3.8-27B. The quantization was produced at RadixArk using NVIDIA Model Optimizer, following a mixed NVFP4 W4A4 recipe. Run on SGLang: launch command and per-platform recipes in the Qwen3.8-27B cookbook. Third-Party Community Consideration 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 for the source model's capabilities, training information, limitations, and license. License/Terms of Use: Apache License 2.0 Deployment Geography: Global <br Use Case: <br Developers looking to deploy an off-the-shelf, pre-quantized model in AI agent systems, chatbots, RAG systems, and other AI-powered applications. <br Release Date: <br Hugging Face 08/14/2026 via https://huggingface.co/RadixArk/Qwen3.8-27B-NVFP4 <br Model Architecture: Architecture Type: Transformers (Dense Multimodal) <br Network Architecture: Qwen3.8-27B <br Number of Model Parameters: 27B <br Input: Input Type(s): Text, image, and video <br Input Format(s): String and visual media <br Other Properties Related to Input: Native context length up to 262,144 tokens. <br Output: Output Type(s): Text <br Output Format: String <br Software Integration: Supported Runtime Engine(s): <br SGLang <br Supported Hardware Microarchitecture Compatibility: <br NVIDIA Blackwell (this checkpoint was produced and validated on GB300) <br Preferred Operating System(s): <br Linux <br Model Version(s): Quantized with NVIDIA Model Optimizer, commit 87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c. <br Training, Testing, and Evaluation Datasets: Calibration Data: Calibration used 1,024 samples from the abisee/cnndailymail training split with sequence length 512. <br Training Dataset: RadixArk did not train or fine-tune this checkpoint. Training information is inherited from the upstream Qwen3.8-27B model card. <br Evaluation Dataset: The model was evaluated on GSM8K and Terminal-Bench 2.1. <br Post Training Quantization The MLP gateproj, upproj, and downproj layers and lmhead use dynamic NVFP4 W4A4 quantization with group size 16. Attention weights use FP8

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys radixark-qwen3-8 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (radixark-qwen3-8 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"radixark-qwen3-8","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models