q3-8b-train_final_v2_nb2_mt8192_replaced_fix
Released by ligeng-dev in 2026, q3-8b-train_final_v2_nb2_mt8192_replaced_fix is a 8 billion parameter chat model. q3-8b-train_final_v2_nb2_mt8192_replaced_fix is an open-weights chat model with roughly 8 billion parameters.
by ligeng-dev · 8B parameters
Best for
Ways to use q3-8b-train_final_v2_nb2_mt8192_replaced_fix in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ligeng-dev API key. osFoundry discovers q3-8b-train_final_v2_nb2_mt8192_replaced_fix 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
q3-8b-train_final_v2_nb2_mt8192_replaced_fix 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 q3-8b-train_final_v2_nb2_mt8192_replaced_fix
q3-8b-train_final_v2_nb2_mt8192_replaced_fix runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~20 GB).
q3-8b-train_final_v2_nb2_mt8192_replaced_fix vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about q3-8b-train_final_v2_nb2_mt8192_replaced_fix
Is q3-8b-train_final_v2_nb2_mt8192_replaced_fix free to use?
q3-8b-train_final_v2_nb2_mt8192_replaced_fix 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 q3-8b-train_final_v2_nb2_mt8192_replaced_fix 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 q3-8b-train_final_v2_nb2_mt8192_replaced_fix need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run q3-8b-train_final_v2_nb2_mt8192_replaced_fix locally?
Yes. q3-8b-train_final_v2_nb2_mt8192_replaced_fix is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is q3-8b-train_final_v2_nb2_mt8192_replaced_fix best at?
q3-8b-train_final_v2_nb2_mt8192_replaced_fix is well-suited to text generation.
How do I use q3-8b-train_final_v2_nb2_mt8192_replaced_fix in osFoundry?
Paste your ligeng-dev API key in the key dialog (or deploy the open weights for self-hostable models), assign q3-8b-train_final_v2_nb2_mt8192_replaced_fix to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ligeng-dev on April 14, 2026. Source: https://huggingface.co/ligeng-dev/q3-8b-train_final_v2_nb2_mt8192_replaced_fix