WoonaV1.2-9b-GGUF-Imatrix
Built by secretmoon, WoonaV1.2-9b-GGUF-Imatrix is a 9 billion parameter chat model. WoonaV1.2-9b-GGUF-Imatrix is an open-weights chat model with roughly 9 billion parameters.
by secretmoon · 9B parameters
Best for
Ways to use WoonaV1.2-9b-GGUF-Imatrix in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your secretmoon API key. osFoundry discovers WoonaV1.2-9b-GGUF-Imatrix 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
WoonaV1.2-9b-GGUF-Imatrix 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 WoonaV1.2-9b-GGUF-Imatrix
WoonaV1.2-9b-GGUF-Imatrix runs on a single 16GB consumer GPU (~6 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~22 GB).
WoonaV1.2-9b-GGUF-Imatrix vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about WoonaV1.2-9b-GGUF-Imatrix
Is WoonaV1.2-9b-GGUF-Imatrix free to use?
WoonaV1.2-9b-GGUF-Imatrix 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 WoonaV1.2-9b-GGUF-Imatrix 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 WoonaV1.2-9b-GGUF-Imatrix need?
Approximately 6 GB at Q4 quantisation, or 22 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run WoonaV1.2-9b-GGUF-Imatrix locally?
Yes. WoonaV1.2-9b-GGUF-Imatrix is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is WoonaV1.2-9b-GGUF-Imatrix best at?
WoonaV1.2-9b-GGUF-Imatrix is well-suited to text generation.
How do I use WoonaV1.2-9b-GGUF-Imatrix in osFoundry?
Paste your secretmoon API key in the key dialog (or deploy the open weights for self-hostable models), assign WoonaV1.2-9b-GGUF-Imatrix to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by secretmoon on August 27, 2024. Source: https://huggingface.co/secretmoon/WoonaV1.2-9b-GGUF-Imatrix