unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone
Built by anemll, unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone is a 26 billion parameter image-generation model. unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone is an open-weights image model with roughly 26 billion parameters.
by anemll · 26B parameters
Best for
Ways to use unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your anemll API key. osFoundry discovers unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone 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
unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone 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 unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone
unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone runs on a single 16GB consumer GPU (~16 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~63 GB).
unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone
Is unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone free to use?
unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone 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 unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone 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 unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone need?
Approximately 16 GB at Q4 quantisation, or 63 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone locally?
Yes. unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone best at?
unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone is well-suited to image text to text.
How do I use unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone in osFoundry?
Paste your anemll API key in the key dialog (or deploy the open weights for self-hostable models), assign unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by anemll on April 5, 2026. Source: https://huggingface.co/anemll/unsloth-gemma-4-26b-a4b-it-UD-MLX-3bit-iphone