Huihui3.5-67B-A3B-abliterated
Released by huihui-ai in 2026, Huihui3.5-67B-A3B-abliterated is a 67 billion parameter image-generation model. Huihui3.5-67B-A3B-abliterated is an open-weights image model with roughly 67 billion parameters.
by huihui-ai · 67B parameters
Best for
Ways to use Huihui3.5-67B-A3B-abliterated in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your huihui-ai API key. osFoundry discovers Huihui3.5-67B-A3B-abliterated 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
Huihui3.5-67B-A3B-abliterated 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 Huihui3.5-67B-A3B-abliterated
Huihui3.5-67B-A3B-abliterated runs on a single A100 80GB or H100 80GB at Q4 quantisation (~41 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~161 GB).
Huihui3.5-67B-A3B-abliterated vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Huihui3.5-67B-A3B-abliterated
Is Huihui3.5-67B-A3B-abliterated free to use?
Huihui3.5-67B-A3B-abliterated 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 Huihui3.5-67B-A3B-abliterated 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 Huihui3.5-67B-A3B-abliterated need?
Approximately 41 GB at Q4 quantisation, or 161 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Huihui3.5-67B-A3B-abliterated locally?
Yes. Huihui3.5-67B-A3B-abliterated is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Huihui3.5-67B-A3B-abliterated best at?
Huihui3.5-67B-A3B-abliterated is well-suited to image text to text.
How do I use Huihui3.5-67B-A3B-abliterated in osFoundry?
Paste your huihui-ai API key in the key dialog (or deploy the open weights for self-hostable models), assign Huihui3.5-67B-A3B-abliterated to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by huihui-ai on April 7, 2026. Source: https://huggingface.co/huihui-ai/Huihui3.5-67B-A3B-abliterated