diff --git a/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx b/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx
index 023360f42..30c92a678 100644
--- a/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx
+++ b/docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx
@@ -42,7 +42,7 @@ Qwen3.5 features a Gated Delta Networks combined with sparse Mixture-of-Experts
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen3.5-397B-A17B</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>[Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B)</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>[Qwen/Qwen3.5-397B-A17B-FP8](https://huggingface.co/Qwen/Qwen3.5-397B-A17B-FP8)</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>NVIDIA NVFP4: [nvidia/Qwen3.5-397B-A17B-NVFP4](https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4)<br/>AMD MXFP4: [amd/Qwen3.5-397B-A17B-MXFP4](https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4)</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>NVIDIA NVFP4: [nvidia/Qwen3.5-397B-A17B-NVFP4-V2](https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4-V2)<br/>AMD MXFP4: [amd/Qwen3.5-397B-A17B-MXFP4](https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4)</td>
     </tr>
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Qwen3.5-122B-A10B</td>
@@ -156,7 +156,7 @@ This section provides deployment configurations optimized for different hardware
         - **MI300X (192GB)** runs with tp=4.
         - **MI325X (256GB)** runs with tp=2.
         - **MI355X (288GB)** runs with tp=2.
-    - **FP4**: The FP4 quantized model requires ~250GB for weights, cutting memory by almost 4x. NVFP4 ([nvidia/Qwen3.5-397B-A17B-NVFP4](https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4)) requires B200/B300 (Blackwell architecture); AMD provides an MXFP4 checkpoint ([amd/Qwen3.5-397B-A17B-MXFP4](https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4)) for MI355X.
+    - **FP4**: The FP4 quantized model requires ~250GB for weights, cutting memory by almost 4x. NVFP4 ([nvidia/Qwen3.5-397B-A17B-NVFP4-V2](https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4-V2)) requires B200/B300 (Blackwell architecture); AMD provides an MXFP4 checkpoint ([amd/Qwen3.5-397B-A17B-MXFP4](https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4)) for MI355X.
         - **B200 (183GB)** runs with tp=4. (NVFP4)
         - **B300 (275GB)** runs with tp=2. (NVFP4)
         - **MI355X (288GB)** runs with tp=2 (use tp=4 for low concurrency). (MXFP4)
diff --git a/docs/src/snippets/autoregressive/qwen35-deployment.jsx b/docs/src/snippets/autoregressive/qwen35-deployment.jsx
index eebdc8881..0ce212be0 100644
--- a/docs/src/snippets/autoregressive/qwen35-deployment.jsx
+++ b/docs/src/snippets/autoregressive/qwen35-deployment.jsx
@@ -318,10 +318,10 @@ export const Qwen35Deployment = () => {
 
     let modelName;
     if (quantization === 'fp4') {
-      // AMD MI355X uses the MXFP4 checkpoint; Blackwell uses NVFP4.
+      // AMD MI355X uses the MXFP4 checkpoint; Blackwell uses NVFP4-V2.
       modelName = hardware === 'mi355x'
         ? 'amd/Qwen3.5-397B-A17B-MXFP4'
-        : 'nvidia/Qwen3.5-397B-A17B-NVFP4';
+        : 'nvidia/Qwen3.5-397B-A17B-NVFP4-V2';
     } else {
       const suffix = MODEL_SUFFIX[model];
       const quantSuffix = quantization === 'fp8' ? '-FP8' : '';