Carnice-27b-MLX-oQ8
0xdfi's Carnice-27b-MLX-oQ8 packs 27 billion parameters into a chat model. Carnice-27b-MLX-oQ8 is an open-weights chat model with roughly 27 billion parameters.
by 0xdfi · 27B parameters
Best for
Ways to use Carnice-27b-MLX-oQ8 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your 0xdfi API key. osFoundry discovers Carnice-27b-MLX-oQ8 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
Carnice-27b-MLX-oQ8 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 Carnice-27b-MLX-oQ8
Carnice-27b-MLX-oQ8 runs on a 24GB consumer or workstation GPU (~17 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~65 GB).
Carnice-27b-MLX-oQ8 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Carnice-27b-MLX-oQ8
Is Carnice-27b-MLX-oQ8 free to use?
Carnice-27b-MLX-oQ8 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 Carnice-27b-MLX-oQ8 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 Carnice-27b-MLX-oQ8 need?
Approximately 17 GB at Q4 quantisation, or 65 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Carnice-27b-MLX-oQ8 locally?
Yes. Carnice-27b-MLX-oQ8 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Carnice-27b-MLX-oQ8 best at?
Carnice-27b-MLX-oQ8 is well-suited to text generation.
How do I use Carnice-27b-MLX-oQ8 in osFoundry?
Paste your 0xdfi API key in the key dialog (or deploy the open weights for self-hostable models), assign Carnice-27b-MLX-oQ8 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by 0xdfi on April 8, 2026. Source: https://huggingface.co/0xdfi/Carnice-27b-MLX-oQ8