Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8
Built by etsien, Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 is a 49 billion parameter chat model. Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 is an open-weights chat model with roughly 49 billion parameters.
by etsien · 49B parameters
Best for
Ways to use Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your etsien API key. osFoundry discovers Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 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
Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 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 Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8
Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 runs on a single A100 40GB at Q4 quantisation (~30 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~118 GB).
Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8
Is Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 free to use?
Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 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 Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 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 Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 need?
Approximately 30 GB at Q4 quantisation, or 118 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 locally?
Yes. Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 best at?
Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 is well-suited to text generation.
How do I use Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 in osFoundry?
Paste your etsien API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by etsien on August 28, 2025. Source: https://huggingface.co/etsien/Llama-3_3-Nemotron-Super-49B-v1_5-GPTQ-w4a8