TeleChat3-Coder-36B-Thinking
Released by Tele-AI in 2026, TeleChat3-Coder-36B-Thinking is a 36 billion parameter chat model. TeleChat3-Coder-36B-Thinking is an open-weights chat model with roughly 36 billion parameters.
by Tele-AI · 36B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use TeleChat3-Coder-36B-Thinking in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Tele-AI API key. osFoundry discovers TeleChat3-Coder-36B-Thinking 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
TeleChat3-Coder-36B-Thinking 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 TeleChat3-Coder-36B-Thinking
TeleChat3-Coder-36B-Thinking runs on a 24GB consumer or workstation GPU (~22 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~87 GB).
TeleChat3-Coder-36B-Thinking vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about TeleChat3-Coder-36B-Thinking
Is TeleChat3-Coder-36B-Thinking free to use?
TeleChat3-Coder-36B-Thinking 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 TeleChat3-Coder-36B-Thinking 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 TeleChat3-Coder-36B-Thinking need?
Approximately 22 GB at Q4 quantisation, or 87 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run TeleChat3-Coder-36B-Thinking locally?
Yes. TeleChat3-Coder-36B-Thinking is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is TeleChat3-Coder-36B-Thinking best at?
TeleChat3-Coder-36B-Thinking is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use TeleChat3-Coder-36B-Thinking in osFoundry?
Paste your Tele-AI API key in the key dialog (or deploy the open weights for self-hostable models), assign TeleChat3-Coder-36B-Thinking to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Tele-AI on January 29, 2026. Source: https://huggingface.co/Tele-AI/TeleChat3-Coder-36B-Thinking