Llama3.2-1.28B-GPTNeoXTokenizer
Built by SloppyModels, Llama3.2-1.28B-GPTNeoXTokenizer is a 1 billion parameter chat model. Llama3.2-1.28B-GPTNeoXTokenizer is an open-weights chat model with roughly 1 billion parameters.
by SloppyModels · 1B parameters
Best for
Ways to use Llama3.2-1.28B-GPTNeoXTokenizer in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your SloppyModels API key. osFoundry discovers Llama3.2-1.28B-GPTNeoXTokenizer 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
Llama3.2-1.28B-GPTNeoXTokenizer 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 Llama3.2-1.28B-GPTNeoXTokenizer
Llama3.2-1.28B-GPTNeoXTokenizer runs on a single 16GB consumer GPU (~1 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~3 GB).
Llama3.2-1.28B-GPTNeoXTokenizer vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama3.2-1.28B-GPTNeoXTokenizer
Is Llama3.2-1.28B-GPTNeoXTokenizer free to use?
Llama3.2-1.28B-GPTNeoXTokenizer 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 Llama3.2-1.28B-GPTNeoXTokenizer 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 Llama3.2-1.28B-GPTNeoXTokenizer need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Llama3.2-1.28B-GPTNeoXTokenizer locally?
Yes. Llama3.2-1.28B-GPTNeoXTokenizer is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama3.2-1.28B-GPTNeoXTokenizer best at?
Llama3.2-1.28B-GPTNeoXTokenizer is well-suited to text generation.
How do I use Llama3.2-1.28B-GPTNeoXTokenizer in osFoundry?
Paste your SloppyModels API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama3.2-1.28B-GPTNeoXTokenizer to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by SloppyModels on April 27, 2026. Source: https://huggingface.co/SloppyModels/Llama3.2-1.28B-GPTNeoXTokenizer