Qwen3.6-35B-A3B-oQ6
Released by ldoroshe in 2026, Qwen3.6-35B-A3B-oQ6 is a 35 billion parameter chat model. Qwen3.6-35B-A3B-oQ6 is an open-weights chat model with roughly 35 billion parameters.
by ldoroshe · 35B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Qwen3.6-35B-A3B-oQ6 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ldoroshe API key. osFoundry discovers Qwen3.6-35B-A3B-oQ6 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
Qwen3.6-35B-A3B-oQ6 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 Qwen3.6-35B-A3B-oQ6
Qwen3.6-35B-A3B-oQ6 runs on a 24GB consumer or workstation GPU (~21 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~84 GB).
Qwen3.6-35B-A3B-oQ6 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3.6-35B-A3B-oQ6
Is Qwen3.6-35B-A3B-oQ6 free to use?
Qwen3.6-35B-A3B-oQ6 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 Qwen3.6-35B-A3B-oQ6 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 Qwen3.6-35B-A3B-oQ6 need?
Approximately 21 GB at Q4 quantisation, or 84 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Qwen3.6-35B-A3B-oQ6 locally?
Yes. Qwen3.6-35B-A3B-oQ6 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3.6-35B-A3B-oQ6 best at?
Qwen3.6-35B-A3B-oQ6 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Qwen3.6-35B-A3B-oQ6 in osFoundry?
Paste your ldoroshe API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3.6-35B-A3B-oQ6 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ldoroshe on April 22, 2026. Source: https://huggingface.co/ldoroshe/Qwen3.6-35B-A3B-oQ6