Qwen-2.5-14b-Kunou-EXL2-4bpw
Statuo's Qwen-2.5-14b-Kunou-EXL2-4bpw packs 14 billion parameters into a chat model. Qwen-2.5-14b-Kunou-EXL2-4bpw is an open-weights chat model with roughly 14 billion parameters.
by Statuo · 14B parameters
Best for
Ways to use Qwen-2.5-14b-Kunou-EXL2-4bpw in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Statuo API key. osFoundry discovers Qwen-2.5-14b-Kunou-EXL2-4bpw 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
Qwen-2.5-14b-Kunou-EXL2-4bpw 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 Qwen-2.5-14b-Kunou-EXL2-4bpw
Qwen-2.5-14b-Kunou-EXL2-4bpw runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~34 GB).
Qwen-2.5-14b-Kunou-EXL2-4bpw vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen-2.5-14b-Kunou-EXL2-4bpw
Is Qwen-2.5-14b-Kunou-EXL2-4bpw free to use?
Qwen-2.5-14b-Kunou-EXL2-4bpw 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 Qwen-2.5-14b-Kunou-EXL2-4bpw 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 Qwen-2.5-14b-Kunou-EXL2-4bpw need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Qwen-2.5-14b-Kunou-EXL2-4bpw locally?
Yes. Qwen-2.5-14b-Kunou-EXL2-4bpw is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen-2.5-14b-Kunou-EXL2-4bpw best at?
Qwen-2.5-14b-Kunou-EXL2-4bpw is well-suited to text generation.
How do I use Qwen-2.5-14b-Kunou-EXL2-4bpw in osFoundry?
Paste your Statuo API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen-2.5-14b-Kunou-EXL2-4bpw to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Statuo on December 15, 2024. Source: https://huggingface.co/Statuo/Qwen-2.5-14b-Kunou-EXL2-4bpw