gpt-oss-120b-awq-w4a16
marcinbrzezanski's gpt-oss-120b-awq-w4a16 packs 120 billion parameters into a chat model. gpt-oss-120b-awq-w4a16 is an open-weights chat model with roughly 120 billion parameters.
by marcinbrzezanski · 120B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use gpt-oss-120b-awq-w4a16 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your marcinbrzezanski API key. osFoundry discovers gpt-oss-120b-awq-w4a16 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-120b-awq-w4a16 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-120b-awq-w4a16
gpt-oss-120b-awq-w4a16 runs on a single A100 80GB or H100 80GB at Q4 quantisation (~72 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~288 GB).
gpt-oss-120b-awq-w4a16 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-120b-awq-w4a16
Is gpt-oss-120b-awq-w4a16 free to use?
gpt-oss-120b-awq-w4a16 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-120b-awq-w4a16 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-120b-awq-w4a16 need?
Approximately 72 GB at Q4 quantisation, or 288 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run gpt-oss-120b-awq-w4a16 locally?
Yes. gpt-oss-120b-awq-w4a16 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gpt-oss-120b-awq-w4a16 best at?
gpt-oss-120b-awq-w4a16 is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use gpt-oss-120b-awq-w4a16 in osFoundry?
Paste your marcinbrzezanski API key in the key dialog (or deploy the open weights for self-hostable models), assign gpt-oss-120b-awq-w4a16 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by marcinbrzezanski on March 4, 2026. Source: https://huggingface.co/marcinbrzezanski/gpt-oss-120b-awq-w4a16