Hy-MT1.5-1.8B-1.25bit
Hy-MT1.5-1.8B-1.25bit (tencent, 2026) is a 2 billion parameter chat model. Hy-MT1.5-1.8B-1.25bit is an open-weights chat model with roughly 2 billion parameters.
by tencent · 2B parameters
Best for
Ways to use Hy-MT1.5-1.8B-1.25bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your tencent API key. osFoundry discovers Hy-MT1.5-1.8B-1.25bit 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
Hy-MT1.5-1.8B-1.25bit 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 Hy-MT1.5-1.8B-1.25bit
Hy-MT1.5-1.8B-1.25bit 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).
Hy-MT1.5-1.8B-1.25bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Hy-MT1.5-1.8B-1.25bit
Is Hy-MT1.5-1.8B-1.25bit free to use?
Hy-MT1.5-1.8B-1.25bit 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 Hy-MT1.5-1.8B-1.25bit 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 Hy-MT1.5-1.8B-1.25bit need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Hy-MT1.5-1.8B-1.25bit locally?
Yes. Hy-MT1.5-1.8B-1.25bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Hy-MT1.5-1.8B-1.25bit best at?
Hy-MT1.5-1.8B-1.25bit is well-suited to translation.
How do I use Hy-MT1.5-1.8B-1.25bit in osFoundry?
Paste your tencent API key in the key dialog (or deploy the open weights for self-hostable models), assign Hy-MT1.5-1.8B-1.25bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by tencent on April 29, 2026. Source: https://huggingface.co/tencent/Hy-MT1.5-1.8B-1.25bit