Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4
Released by mlx-community in 2026, Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 is a 35 billion parameter chat model. Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 is an open-weights chat model with roughly 35 billion parameters.
by mlx-community · 35B parameters
Best for
Ways to use Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mlx-community API key. osFoundry discovers Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 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
Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 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 Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4
Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 runs on a 24GB consumer or workstation GPU (~21 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~84 GB).
Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4
Is Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 free to use?
Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 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 Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 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 Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 need?
Approximately 21 GB at Q4 quantisation, or 84 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 locally?
Yes. Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 best at?
Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 is well-suited to text generation.
How do I use Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 in osFoundry?
Paste your mlx-community API key in the key dialog (or deploy the open weights for self-hostable models), assign Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mlx-community on March 4, 2026. Source: https://huggingface.co/mlx-community/Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4