QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep is a 2 billion parameter chat model from g4me, released April 20, 2026. QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep is an open-weights chat model with roughly 2 billion parameters.
by g4me · 2B parameters
Best for
Ways to use QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your g4me API key. osFoundry discovers QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep 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
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep 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 QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep
Is QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep free to use?
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep 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 QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep 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 QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep locally?
Yes. QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep best at?
QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep is well-suited to text generation.
How do I use QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep in osFoundry?
Paste your g4me API key in the key dialog (or deploy the open weights for self-hostable models), assign QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by g4me on April 20, 2026. Source: https://huggingface.co/g4me/QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-5ep