talkie-1930-13b-it-mlx-6bit
Built by warshanks, talkie-1930-13b-it-mlx-6bit is a 13 billion parameter chat model. talkie-1930-13b-it-mlx-6bit is an open-weights chat model with roughly 13 billion parameters.
by warshanks · 13B parameters
Best for
Ways to use talkie-1930-13b-it-mlx-6bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your warshanks API key. osFoundry discovers talkie-1930-13b-it-mlx-6bit 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
talkie-1930-13b-it-mlx-6bit 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 talkie-1930-13b-it-mlx-6bit
talkie-1930-13b-it-mlx-6bit runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~32 GB).
talkie-1930-13b-it-mlx-6bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about talkie-1930-13b-it-mlx-6bit
Is talkie-1930-13b-it-mlx-6bit free to use?
talkie-1930-13b-it-mlx-6bit 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 talkie-1930-13b-it-mlx-6bit 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 talkie-1930-13b-it-mlx-6bit need?
Approximately 8 GB at Q4 quantisation, or 32 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run talkie-1930-13b-it-mlx-6bit locally?
Yes. talkie-1930-13b-it-mlx-6bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is talkie-1930-13b-it-mlx-6bit best at?
talkie-1930-13b-it-mlx-6bit is well-suited to text generation.
How do I use talkie-1930-13b-it-mlx-6bit in osFoundry?
Paste your warshanks API key in the key dialog (or deploy the open weights for self-hostable models), assign talkie-1930-13b-it-mlx-6bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by warshanks on April 30, 2026. Source: https://huggingface.co/warshanks/talkie-1930-13b-it-mlx-6bit