Compare model versions

Diff

Before

<div align="center">

<a href="https://www.orcarouter.ai" target="_blank">
  <img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
</a>

<h1>Qwen3.8-Flash-Next-Uncensored-NVFP4</h1>

<p><em>NVFP4 (4-bit) weight quantization of the abliterated (refusal-removed) Qwen3.8-Flash-Next &mdash; for Blackwell + vLLM</em></p>

<p>
<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-4C8BF5" alt="License"></a>
<img src="https://img.shields.io/badge/Format-NVFP4%20(compressed--tensors)-00A67E" alt="NVFP4">
<img src="https://img.shields.io/badge/Experts-FP4-FF8800" alt="FP4">
<img src="https://img.shields.io/badge/Attention-FP8-9B59B6" alt="FP8">
<img src="https://img.shields.io/badge/GPU-Blackwell-E67E22" alt="Blackwell">
</p>

<p><strong>One Gateway. Every Model.</strong> &mdash; Route Smarter &middot; Ship Safer &middot; Spend Less.</p>

<p>
<a href="https://www.orcarouter.ai">Website</a> &middot;
<a href="https://www.orcarouter.ai/models">Model Catalog</a> &middot;
<a href="https://github.com/Continuum-AI-Corp">GitHub</a> &middot;
<a href="https://discord.gg/yAh6Tex6kx">Discord</a> &middot;
<a href="https://x.com/OrcaRouter">X</a>
</p>

</div>

---

> **NVFP4 weight quantization** of the **abliterated** (refusal-removed) build of Qwen's
> [`Qwen3.8-Flash-Next`](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) &mdash; a large
> **Mixture-of-Experts** (512 experts, 10 routed + 1 shared active) preview of the **Qwen4 architecture**
> (`qwen4_exp`): Gated DeltaNet linear attention + Qwen Sparse Attention (QSA), HyperConnections, PLE
> n-gram embeddings, native vision-language, reasoning, and tool-calling. The **MoE expert weights are
> quantized to NVFP4 (4-bit, NVIDIA FP4 E2M1, group-16 + FP8 block scales)** and attention/shared-expert
> weights to **FP8**, cutting the model from ~330 GB (bf16) to **~178 GB** while keeping full-precision
> paths where they matter. Browse all models in the [OrcaRouter Model Catalog](https://www.orcarouter.ai/models).

---

After

<div align="center">

<a href="https://www.orcarouter.ai" target="_blank">
  <img src="https://www.orcarouter.ai/orca-logo-classic.png" alt="OrcaRouter" width="110">
</a>

<h1>Qwen3.8-Flash-Next-Uncensored-NVFP4</h1>

<p><em>NVFP4 (4-bit) weight quantization of the abliterated (refusal-removed) Qwen3.8-Flash-Next &mdash; for Blackwell + vLLM</em></p>


<!-- orcacyber-promo:start -->
<table>
<tr>
<td width="150" style="vertical-align: middle;">
<div align="center"><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.0"><img src="https://www.orcarouter.ai/orca-logo-classic.png" width="90" alt="OrcaCyber Zero 1.0"></a></div>
</td>
<td>
<p>🛡️ <strong>New from Orca &mdash; <a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.0">OrcaCyber Zero 1.0</a></strong></p>
<p>Post-trained for cybersecurity: vulnerability analysis, vulnerability reproduction, red teaming &amp; offensive-security research. <strong>98.07% pass@1 on CyberGym Level&nbsp;1</strong> &middot; 1M context &middot; function calling &middot; OpenAI-compatible API.</p>
<p><a href="https://www.orcarouter.ai/models/orca/orcacyber-zero-1.0"><img src="https://img.shields.io/badge/Try%20it%20on%20OrcaRouter%20%E2%86%92-FF6A00?style=for-the-badge&amp;labelColor=0B1F3A" alt="Try it on OrcaRouter"></a></p>
</td>
</tr>
</table>
<!-- orcacyber-promo:end -->

<p>
<a href="https://www.orcarouter.ai"><img src="https://img.shields.io/badge/Website-orcarouter.ai-1E6FEB" alt="Website"></a>
<a href="https://www.orcarouter.ai/models"><img src="https://img.shields.io/badge/OrcaRouter-Model%20Catalog-2EA043" alt="Model Catalog"></a>
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-4C8BF5" alt="License"></a>
<img src="https://img.shields.io/badge/Format-NVFP4%20(compressed--tensors)-00A67E" alt="NVFP4">
<img src="https://img.shields.io/badge/Experts-FP4-FF8800" alt="FP4">
<img src="https://img.shields.io/badge/Attention-FP8-9B59B6" alt="FP8">
<img src="https://img.shields.io/badge/GPU-Blackwell-E67E22" alt="Blackwell">
</p>

<p><strong>One Gateway. Every Model.</strong> &mdash; Route Smarter &middot; Ship Safer &middot; Spend Less.</p>

<p>
<a href="https://www.orcarouter.ai">Website</a> &middot;
<a href="https://www.orcarouter.ai/models">Model Catalog</a> &middot;
<a href="https://github.com/Continuum-AI-Corp">GitHub</a> &middot;
<a href="https://discord.gg/yAh6Tex6kx">Discord</a> &middot;
<a href="https://x.com/OrcaRouter">X</a>
</p>

</div>

---

> **NVFP4 weight quantization** of the **abliterated** (refusal-removed) build of Qwen's
> [`Qwen3.8-Flash-Next`](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) &mdash; a large
> **Mixture-of-Experts** (512 experts, 10 routed + 1 shared active) preview of the **Qwen4 architecture**
> (`qwen4_exp`): Gated DeltaNet linear attention + Qwen Sparse Attention (QSA), HyperConnections, PLE
> n-gram embeddings, native vision-language, reasoning, and tool-calling. The **MoE expert weights are
> quantized to NVFP4 (4-bit, NVIDIA FP4 E2M1, group-16 + FP8 block scales)** and attention/shared-expert
> weights to **FP8**, cutting the model from ~330 GB (bf16) to **~178 GB** while keeping full-precision
> paths where they matter. Browse all models in the [OrcaRouter Model Catalog](https://www.orcarouter.ai/models).

---