gemma-4-E2B-MLX-9bit
gemma-4-E2B-MLX-9bit is a 2 billion parameter chat model from inferencerlabs, released April 2, 2026. gemma-4-E2B-MLX-9bit is an open-weights chat model with roughly 2 billion parameters.
by inferencerlabs · 2B parameters
Best for
Ways to use gemma-4-E2B-MLX-9bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your inferencerlabs API key. osFoundry discovers gemma-4-E2B-MLX-9bit 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
gemma-4-E2B-MLX-9bit 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 gemma-4-E2B-MLX-9bit
gemma-4-E2B-MLX-9bit runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
gemma-4-E2B-MLX-9bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about gemma-4-E2B-MLX-9bit
Is gemma-4-E2B-MLX-9bit free to use?
gemma-4-E2B-MLX-9bit 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 gemma-4-E2B-MLX-9bit 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 gemma-4-E2B-MLX-9bit need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-E2B-MLX-9bit locally?
Yes. gemma-4-E2B-MLX-9bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-E2B-MLX-9bit best at?
gemma-4-E2B-MLX-9bit is well-suited to any to any.
How do I use gemma-4-E2B-MLX-9bit in osFoundry?
Paste your inferencerlabs API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-E2B-MLX-9bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by inferencerlabs on April 2, 2026. Source: https://huggingface.co/inferencerlabs/gemma-4-E2B-MLX-9bit