Qwen3.6-27B-MLX-oQ4-FP16
Released by deepsweet in 2026, Qwen3.6-27B-MLX-oQ4-FP16 is a 27 billion parameter chat model. Qwen3.6-27B-MLX-oQ4-FP16 is an open-weights chat model with roughly 27 billion parameters.
by deepsweet · 27B parameters
Best for
Ways to use Qwen3.6-27B-MLX-oQ4-FP16 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your deepsweet API key. osFoundry discovers Qwen3.6-27B-MLX-oQ4-FP16 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
Qwen3.6-27B-MLX-oQ4-FP16 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 Qwen3.6-27B-MLX-oQ4-FP16
Qwen3.6-27B-MLX-oQ4-FP16 runs on a 24GB consumer or workstation GPU (~17 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~65 GB).
Qwen3.6-27B-MLX-oQ4-FP16 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3.6-27B-MLX-oQ4-FP16
Is Qwen3.6-27B-MLX-oQ4-FP16 free to use?
Qwen3.6-27B-MLX-oQ4-FP16 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 Qwen3.6-27B-MLX-oQ4-FP16 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 Qwen3.6-27B-MLX-oQ4-FP16 need?
Approximately 17 GB at Q4 quantisation, or 65 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Qwen3.6-27B-MLX-oQ4-FP16 locally?
Yes. Qwen3.6-27B-MLX-oQ4-FP16 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3.6-27B-MLX-oQ4-FP16 best at?
Qwen3.6-27B-MLX-oQ4-FP16 is well-suited to text generation.
How do I use Qwen3.6-27B-MLX-oQ4-FP16 in osFoundry?
Paste your deepsweet API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3.6-27B-MLX-oQ4-FP16 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by deepsweet on April 23, 2026. Source: https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-oQ4-FP16