gpt-oss-20b-TurboQuant-MLX-8bit
gpt-oss-20b-TurboQuant-MLX-8bit (majentik, 2026) is a 20 billion parameter chat model. gpt-oss-20b-TurboQuant-MLX-8bit is an open-weights chat model with roughly 20 billion parameters.
by majentik · 20B parameters
Best for
Ways to use gpt-oss-20b-TurboQuant-MLX-8bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your majentik API key. osFoundry discovers gpt-oss-20b-TurboQuant-MLX-8bit 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
gpt-oss-20b-TurboQuant-MLX-8bit 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 gpt-oss-20b-TurboQuant-MLX-8bit
gpt-oss-20b-TurboQuant-MLX-8bit runs on a single 16GB consumer GPU (~12 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~48 GB).
gpt-oss-20b-TurboQuant-MLX-8bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gpt-oss-20b-TurboQuant-MLX-8bit
Is gpt-oss-20b-TurboQuant-MLX-8bit free to use?
gpt-oss-20b-TurboQuant-MLX-8bit 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 gpt-oss-20b-TurboQuant-MLX-8bit 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 gpt-oss-20b-TurboQuant-MLX-8bit need?
Approximately 12 GB at Q4 quantisation, or 48 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gpt-oss-20b-TurboQuant-MLX-8bit locally?
Yes. gpt-oss-20b-TurboQuant-MLX-8bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gpt-oss-20b-TurboQuant-MLX-8bit best at?
gpt-oss-20b-TurboQuant-MLX-8bit is well-suited to text generation.
How do I use gpt-oss-20b-TurboQuant-MLX-8bit in osFoundry?
Paste your majentik API key in the key dialog (or deploy the open weights for self-hostable models), assign gpt-oss-20b-TurboQuant-MLX-8bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by majentik on April 14, 2026. Source: https://huggingface.co/majentik/gpt-oss-20b-TurboQuant-MLX-8bit