MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead
Built by jedisct1, MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead is an chat model. MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead is an open-weights chat model.
by jedisct1
Best for
Ways to use MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jedisct1 API key. osFoundry discovers MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead 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
MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead 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.
MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead
Is MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead free to use?
MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead 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 MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead locally?
Yes. MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead best at?
MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead is well-suited to text generation.
How do I use MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead in osFoundry?
Paste your jedisct1 API key in the key dialog (or deploy the open weights for self-hostable models), assign MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jedisct1 on April 29, 2026. Source: https://huggingface.co/jedisct1/MiMo-V2.5-MLX-first224-moe-gup3-down2-attn4-qhead