SmolLM2-1.7B-Instruct-Q8-mlx
Released by HuggingFaceTB in 2024, SmolLM2-1.7B-Instruct-Q8-mlx is a 2 billion parameter chat model. SmolLM2-1.7B-Instruct-Q8-mlx is an open-weights chat model with roughly 2 billion parameters.
by HuggingFaceTB · 2B parameters
Best for
Ways to use SmolLM2-1.7B-Instruct-Q8-mlx in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your HuggingFaceTB API key. osFoundry discovers SmolLM2-1.7B-Instruct-Q8-mlx 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
SmolLM2-1.7B-Instruct-Q8-mlx 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 SmolLM2-1.7B-Instruct-Q8-mlx
SmolLM2-1.7B-Instruct-Q8-mlx runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
SmolLM2-1.7B-Instruct-Q8-mlx vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SmolLM2-1.7B-Instruct-Q8-mlx
Is SmolLM2-1.7B-Instruct-Q8-mlx free to use?
SmolLM2-1.7B-Instruct-Q8-mlx 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 SmolLM2-1.7B-Instruct-Q8-mlx 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 SmolLM2-1.7B-Instruct-Q8-mlx need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SmolLM2-1.7B-Instruct-Q8-mlx locally?
Yes. SmolLM2-1.7B-Instruct-Q8-mlx is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SmolLM2-1.7B-Instruct-Q8-mlx best at?
SmolLM2-1.7B-Instruct-Q8-mlx is well-suited to text generation.
How do I use SmolLM2-1.7B-Instruct-Q8-mlx in osFoundry?
Paste your HuggingFaceTB API key in the key dialog (or deploy the open weights for self-hostable models), assign SmolLM2-1.7B-Instruct-Q8-mlx to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by HuggingFaceTB on November 27, 2024. Source: https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx