Qwen3-235B-A22B-Instruct-2507
Released by Qwen in 2025, Qwen3-235B-A22B-Instruct-2507 is a 235 billion parameter chat model. Qwen3-235B-A22B-Instruct-2507 is an open-weights chat model with roughly 235 billion parameters.
by Qwen · 235B parameters
Best for
Ways to use Qwen3-235B-A22B-Instruct-2507 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Qwen API key. osFoundry discovers Qwen3-235B-A22B-Instruct-2507 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Qwen3-235B-A22B-Instruct-2507 is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Use Qwen3-235B-A22B-Instruct-2507 via API
Qwen3-235B-A22B-Instruct-2507 is also served by hosted API providers — use it via API (BYOK) if you would rather not manage GPUs. That page lists per-provider pricing.
What hardware can run Qwen3-235B-A22B-Instruct-2507
Qwen3-235B-A22B-Instruct-2507 runs on a multi-GPU setup or H200 141GB at Q4 (~141 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~564 GB).
Qwen3-235B-A22B-Instruct-2507 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3-235B-A22B-Instruct-2507
Is Qwen3-235B-A22B-Instruct-2507 free to use?
Qwen3-235B-A22B-Instruct-2507 is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Qwen3-235B-A22B-Instruct-2507 commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does Qwen3-235B-A22B-Instruct-2507 need?
Approximately 141 GB at Q4 quantisation, or 564 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run Qwen3-235B-A22B-Instruct-2507 locally?
Yes. Qwen3-235B-A22B-Instruct-2507 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3-235B-A22B-Instruct-2507 best at?
Qwen3-235B-A22B-Instruct-2507 is well-suited to text generation.
How do I use Qwen3-235B-A22B-Instruct-2507 in osFoundry?
Paste your Qwen API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3-235B-A22B-Instruct-2507 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Qwen on July 21, 2025. Source: https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507