PIT-4B-FT-202212
Released by Diamegs in 2026, PIT-4B-FT-202212 is a 4 billion parameter chat model. PIT-4B-FT-202212 is an open-weights chat model with roughly 4 billion parameters.
by Diamegs · 4B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use PIT-4B-FT-202212 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Diamegs API key. osFoundry discovers PIT-4B-FT-202212 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
PIT-4B-FT-202212 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 PIT-4B-FT-202212
PIT-4B-FT-202212 runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
PIT-4B-FT-202212 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about PIT-4B-FT-202212
Is PIT-4B-FT-202212 free to use?
PIT-4B-FT-202212 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 PIT-4B-FT-202212 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 PIT-4B-FT-202212 need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run PIT-4B-FT-202212 locally?
Yes. PIT-4B-FT-202212 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is PIT-4B-FT-202212 best at?
PIT-4B-FT-202212 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use PIT-4B-FT-202212 in osFoundry?
Paste your Diamegs API key in the key dialog (or deploy the open weights for self-hostable models), assign PIT-4B-FT-202212 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Diamegs on April 22, 2026. Source: https://huggingface.co/Diamegs/PIT-4B-FT-202212