MinerU2.5-2509-1.2B-mlx-fp16
Built by moonstruxx, MinerU2.5-2509-1.2B-mlx-fp16 is a 1 billion parameter image-generation model. MinerU2.5-2509-1.2B-mlx-fp16 is an open-weights image model with roughly 1 billion parameters.
by moonstruxx · 1B parameters
Best for
Ways to use MinerU2.5-2509-1.2B-mlx-fp16 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your moonstruxx API key. osFoundry discovers MinerU2.5-2509-1.2B-mlx-fp16 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
MinerU2.5-2509-1.2B-mlx-fp16 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 MinerU2.5-2509-1.2B-mlx-fp16
MinerU2.5-2509-1.2B-mlx-fp16 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).
MinerU2.5-2509-1.2B-mlx-fp16 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about MinerU2.5-2509-1.2B-mlx-fp16
Is MinerU2.5-2509-1.2B-mlx-fp16 free to use?
MinerU2.5-2509-1.2B-mlx-fp16 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 MinerU2.5-2509-1.2B-mlx-fp16 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 MinerU2.5-2509-1.2B-mlx-fp16 need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run MinerU2.5-2509-1.2B-mlx-fp16 locally?
Yes. MinerU2.5-2509-1.2B-mlx-fp16 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is MinerU2.5-2509-1.2B-mlx-fp16 best at?
MinerU2.5-2509-1.2B-mlx-fp16 is well-suited to image text to text.
How do I use MinerU2.5-2509-1.2B-mlx-fp16 in osFoundry?
Paste your moonstruxx API key in the key dialog (or deploy the open weights for self-hostable models), assign MinerU2.5-2509-1.2B-mlx-fp16 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by moonstruxx on September 29, 2025. Source: https://huggingface.co/moonstruxx/MinerU2.5-2509-1.2B-mlx-fp16