nyun-c2-llama3-56B
nyun-c2-llama3-56B is a 56 billion parameter chat model from nyunai, released June 14, 2024. nyun-c2-llama3-56B is an open-weights chat model with roughly 56 billion parameters.
by nyunai · 56B parameters
Best for
Ways to use nyun-c2-llama3-56B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your nyunai API key. osFoundry discovers nyun-c2-llama3-56B 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
nyun-c2-llama3-56B 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 nyun-c2-llama3-56B
nyun-c2-llama3-56B runs on a single A100 40GB at Q4 quantisation (~34 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~135 GB).
nyun-c2-llama3-56B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about nyun-c2-llama3-56B
Is nyun-c2-llama3-56B free to use?
nyun-c2-llama3-56B 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 nyun-c2-llama3-56B 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 nyun-c2-llama3-56B need?
Approximately 34 GB at Q4 quantisation, or 135 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run nyun-c2-llama3-56B locally?
Yes. nyun-c2-llama3-56B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is nyun-c2-llama3-56B best at?
nyun-c2-llama3-56B is well-suited to text generation.
How do I use nyun-c2-llama3-56B in osFoundry?
Paste your nyunai API key in the key dialog (or deploy the open weights for self-hostable models), assign nyun-c2-llama3-56B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by nyunai on June 14, 2024. Source: https://huggingface.co/nyunai/nyun-c2-llama3-56B