---
type: "raw_signal"
id: "nvidia-model-optimizer-ae1a04"
slug: "nvidia-model-optimizer-ae1a04"
title: "NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4"
description: "NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4 W4A4 post-training quantization with quantization-aware distillation."
retrieval_nugget: "NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4 W4A4 post-training quantization with quantization-aware distillation."
observed_at: "2026-09-24"
record_date: "2026-09-24"
date_kind: "observed_at"
why_it_matters: "Source: https://github.com/NVIDIA/Model-Optimizer"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "github.com"
topics: []
entities: []
related_patterns: []
source_url: "https://github.com/NVIDIA/Model-Optimizer"
source_urls: ["https://github.com/NVIDIA/Model-Optimizer"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:nvidia-model-optimizer-ae1a04"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/nvidia-model-optimizer-ae1a04/","markdown":"https://newruntime.com/signals/nvidia-model-optimizer-ae1a04.md","json":"https://newruntime.com/signals/nvidia-model-optimizer-ae1a04.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4

## Retrieval answer

NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4 W4A4 post-training quantization with quantization-aware distillation.

NVIDIA’s Model Optimizer repository now includes an end-to-end tutorial for Qwen3.6-35B-A3B combining NVFP4 W4A4 post-training quantization with quantization-aware distillation. NVIDIA reports up to 1.30× vLLM throughput versus BF16, 3.1× smaller checkpoints, and accuracy recovery from the aggressive W4A4 conversion. The library composes optimization methods and exports quantized checkpoints for inference frameworks including SGLang, TensorRT-LLM, TensorRT, and vLLM.

Source: https://github.com/NVIDIA/Model-Optimizer

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)