GTLM-1-2B-A350M
Madras1's GTLM-1-2B-A350M packs 2 billion parameters into a chat model. GTLM-1-2B-A350M is an open-weights chat model with roughly 2 billion parameters.
by Madras1 · 2B parameters
Best for
Ways to use GTLM-1-2B-A350M in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Madras1 API key. osFoundry discovers GTLM-1-2B-A350M 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
GTLM-1-2B-A350M 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 GTLM-1-2B-A350M
GTLM-1-2B-A350M 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).
GTLM-1-2B-A350M vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about GTLM-1-2B-A350M
Is GTLM-1-2B-A350M free to use?
GTLM-1-2B-A350M 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 GTLM-1-2B-A350M 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 GTLM-1-2B-A350M need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run GTLM-1-2B-A350M locally?
Yes. GTLM-1-2B-A350M is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is GTLM-1-2B-A350M best at?
GTLM-1-2B-A350M is well-suited to text generation.
How do I use GTLM-1-2B-A350M in osFoundry?
Paste your Madras1 API key in the key dialog (or deploy the open weights for self-hostable models), assign GTLM-1-2B-A350M to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Madras1 on December 14, 2025. Source: https://huggingface.co/Madras1/GTLM-1-2B-A350M