Mistral-Small-4-119B-2603-5bit
Mistral-Small-4-119B-2603-5bit is a 119 billion parameter chat model from mlx-community, released March 17, 2026. Mistral-Small-4-119B-2603-5bit is an open-weights chat model with roughly 119 billion parameters.
by mlx-community · 119B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Mistral-Small-4-119B-2603-5bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mlx-community API key. osFoundry discovers Mistral-Small-4-119B-2603-5bit 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-Small-4-119B-2603-5bit 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-Small-4-119B-2603-5bit
Mistral-Small-4-119B-2603-5bit runs on a single A100 80GB or H100 80GB at Q4 quantisation (~72 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~286 GB).
Mistral-Small-4-119B-2603-5bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Mistral-Small-4-119B-2603-5bit
Is Mistral-Small-4-119B-2603-5bit free to use?
Mistral-Small-4-119B-2603-5bit 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-Small-4-119B-2603-5bit 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-Small-4-119B-2603-5bit need?
Approximately 72 GB at Q4 quantisation, or 286 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Mistral-Small-4-119B-2603-5bit locally?
Yes. Mistral-Small-4-119B-2603-5bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Mistral-Small-4-119B-2603-5bit best at?
Mistral-Small-4-119B-2603-5bit is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Mistral-Small-4-119B-2603-5bit in osFoundry?
Paste your mlx-community API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral-Small-4-119B-2603-5bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mlx-community on March 17, 2026. Source: https://huggingface.co/mlx-community/Mistral-Small-4-119B-2603-5bit