Gemopus-4-31B-it-MLX-4bit-nvfp4
Gemopus-4-31B-it-MLX-4bit-nvfp4 (zecanard, 2026) is a 31 billion parameter chat model. Gemopus-4-31B-it-MLX-4bit-nvfp4 is an open-weights chat model with roughly 31 billion parameters.
by zecanard · 31B parameters
Best for
Ways to use Gemopus-4-31B-it-MLX-4bit-nvfp4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your zecanard API key. osFoundry discovers Gemopus-4-31B-it-MLX-4bit-nvfp4 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
Gemopus-4-31B-it-MLX-4bit-nvfp4 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 Gemopus-4-31B-it-MLX-4bit-nvfp4
Gemopus-4-31B-it-MLX-4bit-nvfp4 runs on a 24GB consumer or workstation GPU (~19 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~75 GB).
Gemopus-4-31B-it-MLX-4bit-nvfp4 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Gemopus-4-31B-it-MLX-4bit-nvfp4
Is Gemopus-4-31B-it-MLX-4bit-nvfp4 free to use?
Gemopus-4-31B-it-MLX-4bit-nvfp4 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 Gemopus-4-31B-it-MLX-4bit-nvfp4 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 Gemopus-4-31B-it-MLX-4bit-nvfp4 need?
Approximately 19 GB at Q4 quantisation, or 75 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Gemopus-4-31B-it-MLX-4bit-nvfp4 locally?
Yes. Gemopus-4-31B-it-MLX-4bit-nvfp4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Gemopus-4-31B-it-MLX-4bit-nvfp4 best at?
Gemopus-4-31B-it-MLX-4bit-nvfp4 is well-suited to text generation.
How do I use Gemopus-4-31B-it-MLX-4bit-nvfp4 in osFoundry?
Paste your zecanard API key in the key dialog (or deploy the open weights for self-hostable models), assign Gemopus-4-31B-it-MLX-4bit-nvfp4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by zecanard on April 15, 2026. Source: https://huggingface.co/zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4