FLM-2-52B-Instruct-2407
Built by CofeAI, FLM-2-52B-Instruct-2407 is a 52 billion parameter embedding model. FLM-2-52B-Instruct-2407 is an open-weights embed model with roughly 52 billion parameters.
by CofeAI · 52B parameters
Best for
Ways to use FLM-2-52B-Instruct-2407 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your CofeAI API key. osFoundry discovers FLM-2-52B-Instruct-2407 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
FLM-2-52B-Instruct-2407 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 FLM-2-52B-Instruct-2407
FLM-2-52B-Instruct-2407 runs on a single A100 40GB at Q4 quantisation (~32 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~125 GB).
FLM-2-52B-Instruct-2407 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about FLM-2-52B-Instruct-2407
Is FLM-2-52B-Instruct-2407 free to use?
FLM-2-52B-Instruct-2407 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 FLM-2-52B-Instruct-2407 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 FLM-2-52B-Instruct-2407 need?
Approximately 32 GB at Q4 quantisation, or 125 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run FLM-2-52B-Instruct-2407 locally?
Yes. FLM-2-52B-Instruct-2407 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is FLM-2-52B-Instruct-2407 best at?
FLM-2-52B-Instruct-2407 is well-suited to feature extraction.
How do I use FLM-2-52B-Instruct-2407 in osFoundry?
Paste your CofeAI API key in the key dialog (or deploy the open weights for self-hostable models), assign FLM-2-52B-Instruct-2407 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by CofeAI on July 22, 2024. Source: https://huggingface.co/CofeAI/FLM-2-52B-Instruct-2407