K2-Prover-SFT-8B-LORA
DiffLean's K2-Prover-SFT-8B-LORA packs 8 billion parameters into a chat model. K2-Prover-SFT-8B-LORA is an open-weights chat model with roughly 8 billion parameters.
by DiffLean · 8B parameters
Best for
Ways to use K2-Prover-SFT-8B-LORA in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your DiffLean API key. osFoundry discovers K2-Prover-SFT-8B-LORA 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
K2-Prover-SFT-8B-LORA 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 K2-Prover-SFT-8B-LORA
K2-Prover-SFT-8B-LORA runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~20 GB).
K2-Prover-SFT-8B-LORA vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about K2-Prover-SFT-8B-LORA
Is K2-Prover-SFT-8B-LORA free to use?
K2-Prover-SFT-8B-LORA 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 K2-Prover-SFT-8B-LORA 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 K2-Prover-SFT-8B-LORA need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run K2-Prover-SFT-8B-LORA locally?
Yes. K2-Prover-SFT-8B-LORA is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is K2-Prover-SFT-8B-LORA best at?
K2-Prover-SFT-8B-LORA is well-suited to text generation.
How do I use K2-Prover-SFT-8B-LORA in osFoundry?
Paste your DiffLean API key in the key dialog (or deploy the open weights for self-hostable models), assign K2-Prover-SFT-8B-LORA to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by DiffLean on April 28, 2026. Source: https://huggingface.co/DiffLean/K2-Prover-SFT-8B-LORA