Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8
Released by mlx-community in 2025, Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 is a 30 billion parameter chat model. Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 is an open-weights chat model with roughly 30 billion parameters.
by mlx-community · 30B parameters
Best for
Ways to use Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mlx-community API key. osFoundry discovers Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8
Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8
Is Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 free to use?
Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 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-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 locally?
Yes. Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 best at?
Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 is well-suited to text generation.
How do I use Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 in osFoundry?
Paste your mlx-community API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mlx-community on August 1, 2025. Source: https://huggingface.co/mlx-community/Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8