Skip to content

Qwen3.5 NVFP4 V2 #32945

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ishandhanani merged 1 commit into from
Aug 7, 2026
+4 −4
Merged

Qwen3.5 NVFP4 V2 #32945

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -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)
Expand Down
4 changes: 2 additions & 2 deletions docs/src/snippets/autoregressive/qwen35-deployment.jsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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' : '';
Expand Down