Param2-17B-A2.4B-Thinking
Released by bharatgenai in 2026, Param2-17B-A2.4B-Thinking is a 17 billion parameter chat model. Param2-17B-A2.4B-Thinking is an open-weights chat model with roughly 17 billion parameters.
by bharatgenai · 17B parameters
Best for
Ways to use Param2-17B-A2.4B-Thinking in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your bharatgenai API key. osFoundry discovers Param2-17B-A2.4B-Thinking 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
Param2-17B-A2.4B-Thinking 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 Param2-17B-A2.4B-Thinking
Param2-17B-A2.4B-Thinking runs on a single 16GB consumer GPU (~11 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~41 GB).
Param2-17B-A2.4B-Thinking vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Param2-17B-A2.4B-Thinking
Is Param2-17B-A2.4B-Thinking free to use?
Param2-17B-A2.4B-Thinking 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 Param2-17B-A2.4B-Thinking 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 Param2-17B-A2.4B-Thinking need?
Approximately 11 GB at Q4 quantisation, or 41 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Param2-17B-A2.4B-Thinking locally?
Yes. Param2-17B-A2.4B-Thinking is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Param2-17B-A2.4B-Thinking best at?
Param2-17B-A2.4B-Thinking is well-suited to text generation.
How do I use Param2-17B-A2.4B-Thinking in osFoundry?
Paste your bharatgenai API key in the key dialog (or deploy the open weights for self-hostable models), assign Param2-17B-A2.4B-Thinking to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by bharatgenai on February 16, 2026. Source: https://huggingface.co/bharatgenai/Param2-17B-A2.4B-Thinking