openai_gpt-oss-20b-GGUF-MXFP4-Experimental
openai_gpt-oss-20b-GGUF-MXFP4-Experimental is a 20 billion parameter chat model from bartowski, released August 5, 2025. openai_gpt-oss-20b-GGUF-MXFP4-Experimental is an open-weights chat model with roughly 20 billion parameters.
by bartowski · 20B parameters
Best for
Ways to use openai_gpt-oss-20b-GGUF-MXFP4-Experimental in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your bartowski API key. osFoundry discovers openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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
openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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 openai_gpt-oss-20b-GGUF-MXFP4-Experimental
openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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).
openai_gpt-oss-20b-GGUF-MXFP4-Experimental vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about openai_gpt-oss-20b-GGUF-MXFP4-Experimental
Is openai_gpt-oss-20b-GGUF-MXFP4-Experimental free to use?
openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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 openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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 openai_gpt-oss-20b-GGUF-MXFP4-Experimental need?
Approximately 12 GB at Q4 quantisation, or 48 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run openai_gpt-oss-20b-GGUF-MXFP4-Experimental locally?
Yes. openai_gpt-oss-20b-GGUF-MXFP4-Experimental is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is openai_gpt-oss-20b-GGUF-MXFP4-Experimental best at?
openai_gpt-oss-20b-GGUF-MXFP4-Experimental is well-suited to text generation.
How do I use openai_gpt-oss-20b-GGUF-MXFP4-Experimental in osFoundry?
Paste your bartowski API key in the key dialog (or deploy the open weights for self-hostable models), assign openai_gpt-oss-20b-GGUF-MXFP4-Experimental to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by bartowski on August 5, 2025. Source: https://huggingface.co/bartowski/openai_gpt-oss-20b-GGUF-MXFP4-Experimental