llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320
Built by KKHYA, llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 is a 2 billion parameter chat model. llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 is an open-weights chat model with roughly 2 billion parameters.
by KKHYA · 2B parameters
Best for
Ways to use llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your KKHYA API key. osFoundry discovers llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 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
llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 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 llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320
llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 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).
llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320
Is llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 free to use?
llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 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 llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 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 llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 locally?
Yes. llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 best at?
llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 is well-suited to text generation.
How do I use llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 in osFoundry?
Paste your KKHYA API key in the key dialog (or deploy the open weights for self-hostable models), assign llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by KKHYA on April 27, 2026. Source: https://huggingface.co/KKHYA/llavaqwen3-1.7b-finetune-moe-4e-2k_20260427_233320