qwen_3.5_0.8b-capybara_numbers_ft_full
Released by DesKate in 2026, qwen_3.5_0.8b-capybara_numbers_ft_full is a 1 billion parameter image-generation model. qwen_3.5_0.8b-capybara_numbers_ft_full is an open-weights image model with roughly 1 billion parameters.
by DesKate · 1B parameters
Best for
Ways to use qwen_3.5_0.8b-capybara_numbers_ft_full in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your DesKate API key. osFoundry discovers qwen_3.5_0.8b-capybara_numbers_ft_full 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
qwen_3.5_0.8b-capybara_numbers_ft_full 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 qwen_3.5_0.8b-capybara_numbers_ft_full
qwen_3.5_0.8b-capybara_numbers_ft_full 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).
qwen_3.5_0.8b-capybara_numbers_ft_full vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about qwen_3.5_0.8b-capybara_numbers_ft_full
Is qwen_3.5_0.8b-capybara_numbers_ft_full free to use?
qwen_3.5_0.8b-capybara_numbers_ft_full 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 qwen_3.5_0.8b-capybara_numbers_ft_full 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 qwen_3.5_0.8b-capybara_numbers_ft_full need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run qwen_3.5_0.8b-capybara_numbers_ft_full locally?
Yes. qwen_3.5_0.8b-capybara_numbers_ft_full is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is qwen_3.5_0.8b-capybara_numbers_ft_full best at?
qwen_3.5_0.8b-capybara_numbers_ft_full is well-suited to image text to text.
How do I use qwen_3.5_0.8b-capybara_numbers_ft_full in osFoundry?
Paste your DesKate API key in the key dialog (or deploy the open weights for self-hostable models), assign qwen_3.5_0.8b-capybara_numbers_ft_full to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by DesKate on April 25, 2026. Source: https://huggingface.co/DesKate/qwen_3.5_0.8b-capybara_numbers_ft_full