Mistral-Medium-3.5-128B-BF16-Text-Only
Released by Darkhn in 2026, Mistral-Medium-3.5-128B-BF16-Text-Only is a 128 billion parameter chat model. Mistral-Medium-3.5-128B-BF16-Text-Only is an open-weights chat model with roughly 128 billion parameters.
by Darkhn · 128B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Mistral-Medium-3.5-128B-BF16-Text-Only in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Darkhn API key. osFoundry discovers Mistral-Medium-3.5-128B-BF16-Text-Only 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-BF16-Text-Only 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-BF16-Text-Only
Mistral-Medium-3.5-128B-BF16-Text-Only 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-BF16-Text-Only 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-BF16-Text-Only
Is Mistral-Medium-3.5-128B-BF16-Text-Only free to use?
Mistral-Medium-3.5-128B-BF16-Text-Only 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-BF16-Text-Only 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-BF16-Text-Only 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-BF16-Text-Only locally?
Yes. Mistral-Medium-3.5-128B-BF16-Text-Only 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-BF16-Text-Only best at?
Mistral-Medium-3.5-128B-BF16-Text-Only is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Mistral-Medium-3.5-128B-BF16-Text-Only in osFoundry?
Paste your Darkhn API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral-Medium-3.5-128B-BF16-Text-Only to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Darkhn on April 29, 2026. Source: https://huggingface.co/Darkhn/Mistral-Medium-3.5-128B-BF16-Text-Only