Who is Qwen3 235B A22B for?

Qwen3 235B A22B is an open-source project built for developers.

Does Qwen3 235B A22B have a free plan?

Yes — Qwen3 235B A22B is open source under the Apache-2.0 license and free to use.

What platforms does Qwen3 235B A22B run on?

Qwen3 235B A22B runs on the web, the command line, and API. It can also be self-hosted.

Is Qwen3 235B A22B still maintained?

The GitHub repository shows 350 commits in the last 90 days.

What are alternatives to Qwen3 235B A22B?

Similar projects tracked by PulseGate include Qwen3.5 397B A17B, Qwen3 32B, and Qwen3.6 35B A3B.

Who develops Qwen3 235B A22B?

Qwen3 235B A22B is developed by NVIDIA.

How long has Qwen3 235B A22B been around?

Qwen3 235B A22B first shipped in 2024.

Back to the index

Qwen3 235B A22B

Name: Qwen3 235B A22B
Author: NVIDIA

huggingface.coInfrastructure

Qwen3-235B-A22B-NVFP4 is a massive open-weights Mixture-of-Experts (MoE) model from the Qwen3 family, quantized to NVFP4 precision for NVIDIA hardware. It supports advanced capabilities including tool calling and multi-step reasoning. The model is hosted on Hugging Face and is intended for local or self-hosted deployment by developers building applications that require high-capability language understanding and agentic behavior.

Open SourceApache-2.0WebCLIAPISelf-hosted

Visit huggingface.co

3.3kstars

509forks

18alternatives

4features

2024since

Overview

4 features

In the Foundation models & chat space, Qwen3 235B A22B takes a focused approach. It focuses on running very large language models efficiently on NVIDIA GPUs with reduced precision for lower memory usage and faster inference. Qwen3 235B A22B is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API, and it can be self-hosted.

It is developed by NVIDIA, and it first shipped in 2024. Development happens publicly on GitHub with 3.3k stars and 350 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 18 similar projects. Key capabilities include Tool Calling, Function Calling, and Multi-step Reasoning.

Summary written by a language model from the project’s public pages.

Tool Calling
Function Calling
Multi-step Reasoning
Mixture of Experts

Built with & integrations

Hosting

AWS

AI providers

local_oss

Runs on

BrowserCLIAPI-onlySelf-hosted

Detected from

AWS: x-amz-cf-id header · x-amz-cf-pop header · via header

Trust & compliance

License

Apache-2.0

Verified signals

HTTPSPrivacy Policy Terms of ServiceOpen SourceActive maintenance

Legal

Indexing history

What PulseGate has recorded for this listing

Indexed23 Jul · 10:27 UTC
nvidia/Qwen3-235B-A22B-NVFP4 verified against its public source
Source: PulseGate · Open

Frequently asked questions about Qwen3 235B A22B

What does Qwen3 235B A22B do?: Qwen3 235B A22B focuses on running very large language models efficiently on NVIDIA GPUs with reduced precision for lower memory usage and faster inference. It is catalogued under Foundation models & chat on PulseGate.
Who is Qwen3 235B A22B for?: Qwen3 235B A22B is an open-source project built for developers.
Does Qwen3 235B A22B have a free plan?: Yes — Qwen3 235B A22B is open source under the Apache-2.0 license and free to use.
What platforms does Qwen3 235B A22B run on?: Qwen3 235B A22B runs on the web, the command line, and API. It can also be self-hosted.
Is Qwen3 235B A22B still maintained?: The GitHub repository shows 350 commits in the last 90 days.
What are alternatives to Qwen3 235B A22B?: Similar projects tracked by PulseGate include Qwen3.5 397B A17B, Qwen3 32B, and Qwen3.6 35B A3B.Qwen3.5 397B A17B Qwen3 32B Qwen3.6 35B A3B
Who develops Qwen3 235B A22B?: Qwen3 235B A22B is developed by NVIDIA.
How long has Qwen3 235B A22B been around?: Qwen3 235B A22B first shipped in 2024.

At a glance

Pricing: Open Source
Platforms: Web
Languages: English
License: Apache-2.0
Built for: developers
Model: Open source
Solves: Running very large language models efficiently on NVIDIA GPUs with reduced precision for lower memory usage and faster inference.

Registered as

Hugging Face: nvidia/Qwen3-235B-A22B-NVFP4

Developer

NVIDIA

Community-driven

Open source

Stars: 3,295
Forks: 509
Open issues: 320
Last commit: 23 Jul 2026
Commits 90d: 350
Contributors: 83
Authorship: Community-driven
Default branch: main
Latest release: 0.45.0 · 6 Jul 2026

Live coverage

Identity confidence: Medium · 70.4
Indexed: 23 Jul 2026
Lifecycle: Alive
Last seen: 23 Jul 2026

Identity audit (13)

Slug: nvidia-qwen3-235b-a22b-nvfp4-huggingface-co
Lifecycle state recorded: 23 Jul 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 23 Jul 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Derived from the project's own page and URL.
Category from: Derived from the model's own Hugging Face metadata.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Last updated: 4 Aug 2026
Canonical URL: https://huggingface.co/nvidia/Qwen3-235B-A22B-NVFP4

Ship this? Send a correction — no account, and you get a link to follow it.

Similar apps

Closest matches by what these projects do