Qwen3-30B-A3B-Instruct-2507-REAM
Released by SamsungSAILMontreal in 2026, Qwen3-30B-A3B-Instruct-2507-REAM is a 30 billion parameter chat model. Qwen3-30B-A3B-Instruct-2507-REAM is an open-weights chat model with roughly 30 billion parameters.
by SamsungSAILMontreal · 30B parameters
Best for
Ways to use Qwen3-30B-A3B-Instruct-2507-REAM in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your SamsungSAILMontreal API key. osFoundry discovers Qwen3-30B-A3B-Instruct-2507-REAM 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
Qwen3-30B-A3B-Instruct-2507-REAM 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.
What hardware can run Qwen3-30B-A3B-Instruct-2507-REAM
Qwen3-30B-A3B-Instruct-2507-REAM runs on a 24GB consumer or workstation GPU (~18 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~72 GB).
Qwen3-30B-A3B-Instruct-2507-REAM vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3-30B-A3B-Instruct-2507-REAM
Is Qwen3-30B-A3B-Instruct-2507-REAM free to use?
Qwen3-30B-A3B-Instruct-2507-REAM 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 Qwen3-30B-A3B-Instruct-2507-REAM 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 Qwen3-30B-A3B-Instruct-2507-REAM need?
Approximately 18 GB at Q4 quantisation, or 72 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Qwen3-30B-A3B-Instruct-2507-REAM locally?
Yes. Qwen3-30B-A3B-Instruct-2507-REAM is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3-30B-A3B-Instruct-2507-REAM best at?
Qwen3-30B-A3B-Instruct-2507-REAM is well-suited to text generation.
How do I use Qwen3-30B-A3B-Instruct-2507-REAM in osFoundry?
Paste your SamsungSAILMontreal API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3-30B-A3B-Instruct-2507-REAM to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by SamsungSAILMontreal on January 14, 2026. Source: https://huggingface.co/SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM