Mistral-Medium-3.5-128B-TQ3
kcnpxcp's Mistral-Medium-3.5-128B-TQ3 packs 128 billion parameters into a image-generation model. Mistral-Medium-3.5-128B-TQ3 is an open-weights image model with roughly 128 billion parameters.
by kcnpxcp · 128B parameters
Best for
Ways to use Mistral-Medium-3.5-128B-TQ3 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your kcnpxcp API key. osFoundry discovers Mistral-Medium-3.5-128B-TQ3 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
Mistral-Medium-3.5-128B-TQ3 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 Mistral-Medium-3.5-128B-TQ3
Mistral-Medium-3.5-128B-TQ3 runs on a single A100 80GB or H100 80GB at Q4 quantisation (~77 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~308 GB).
Mistral-Medium-3.5-128B-TQ3 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Mistral-Medium-3.5-128B-TQ3
Is Mistral-Medium-3.5-128B-TQ3 free to use?
Mistral-Medium-3.5-128B-TQ3 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 Mistral-Medium-3.5-128B-TQ3 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 Mistral-Medium-3.5-128B-TQ3 need?
Approximately 77 GB at Q4 quantisation, or 308 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Mistral-Medium-3.5-128B-TQ3 locally?
Yes. Mistral-Medium-3.5-128B-TQ3 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Mistral-Medium-3.5-128B-TQ3 best at?
Mistral-Medium-3.5-128B-TQ3 is well-suited to image text to text.
How do I use Mistral-Medium-3.5-128B-TQ3 in osFoundry?
Paste your kcnpxcp API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral-Medium-3.5-128B-TQ3 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by kcnpxcp on May 2, 2026. Source: https://huggingface.co/kcnpxcp/Mistral-Medium-3.5-128B-TQ3