SaulLM-54B-Instruct
SaulLM-54B-Instruct is a 54 billion parameter chat model from Equall, released May 7, 2024. SaulLM-54B-Instruct is an open-weights chat model with roughly 54 billion parameters.
by Equall · 54B parameters
Best for
Ways to use SaulLM-54B-Instruct in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Equall API key. osFoundry discovers SaulLM-54B-Instruct 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
SaulLM-54B-Instruct 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 SaulLM-54B-Instruct
SaulLM-54B-Instruct runs on a single A100 40GB at Q4 quantisation (~33 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~130 GB).
SaulLM-54B-Instruct vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SaulLM-54B-Instruct
Is SaulLM-54B-Instruct free to use?
SaulLM-54B-Instruct 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 SaulLM-54B-Instruct 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 SaulLM-54B-Instruct need?
Approximately 33 GB at Q4 quantisation, or 130 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run SaulLM-54B-Instruct locally?
Yes. SaulLM-54B-Instruct is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SaulLM-54B-Instruct best at?
SaulLM-54B-Instruct is well-suited to text generation.
How do I use SaulLM-54B-Instruct in osFoundry?
Paste your Equall API key in the key dialog (or deploy the open weights for self-hostable models), assign SaulLM-54B-Instruct to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Equall on May 7, 2024. Source: https://huggingface.co/Equall/SaulLM-54B-Instruct