kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF (Flexan, 2026) is a 1 billion parameter image-generation model. kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF is an open-weights image model with roughly 1 billion parameters.
by Flexan · 1B parameters
Best for
Ways to use kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Flexan API key. osFoundry discovers kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF 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
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF 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 kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF runs on a single 16GB consumer GPU (~1 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~3 GB).
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF
Is kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF free to use?
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF 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 kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF 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 kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF locally?
Yes. kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF best at?
kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF is well-suited to image text to text.
How do I use kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF in osFoundry?
Paste your Flexan API key in the key dialog (or deploy the open weights for self-hostable models), assign kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Flexan on March 13, 2026. Source: https://huggingface.co/Flexan/kshitijthakkar-qwen3.5-moe-0.87B-d0.8B-GGUF