gemma-4-E4B-it-abliterix
gemma-4-E4B-it-abliterix is a 4 billion parameter chat model from wangzhang, released April 10, 2026. gemma-4-E4B-it-abliterix is an open-weights chat model with roughly 4 billion parameters.
by wangzhang · 4B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use gemma-4-E4B-it-abliterix in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your wangzhang API key. osFoundry discovers gemma-4-E4B-it-abliterix 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-E4B-it-abliterix 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-E4B-it-abliterix
gemma-4-E4B-it-abliterix runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
gemma-4-E4B-it-abliterix 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-E4B-it-abliterix
Is gemma-4-E4B-it-abliterix free to use?
gemma-4-E4B-it-abliterix 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-E4B-it-abliterix 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-E4B-it-abliterix need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run gemma-4-E4B-it-abliterix locally?
Yes. gemma-4-E4B-it-abliterix is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is gemma-4-E4B-it-abliterix best at?
gemma-4-E4B-it-abliterix is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use gemma-4-E4B-it-abliterix in osFoundry?
Paste your wangzhang API key in the key dialog (or deploy the open weights for self-hostable models), assign gemma-4-E4B-it-abliterix to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by wangzhang on April 10, 2026. Source: https://huggingface.co/wangzhang/gemma-4-E4B-it-abliterix