SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI
Released by lmsys in 2025, SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI is a 480 billion parameter chat model. SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI is an open-weights chat model with roughly 480 billion parameters.
by lmsys · 480B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your lmsys API key. osFoundry discovers SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI 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
SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI 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 SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI
SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI runs on a multi-GPU setup or H200 141GB at Q4 (~288 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~1152 GB).
SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI
Is SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI free to use?
SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI 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 SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI 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 SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI need?
Approximately 288 GB at Q4 quantisation, or 1152 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI locally?
Yes. SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI best at?
SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI in osFoundry?
Paste your lmsys API key in the key dialog (or deploy the open weights for self-hostable models), assign SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by lmsys on December 22, 2025. Source: https://huggingface.co/lmsys/SGLang-EAGLE3-Qwen3-Coder-480B-A35B-Instruct-SpecForge-EigenAI